© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128908
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to rare or specialized tokens, i.e. unusual terms or technical words that occur infrequently.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    retrospective, prospective, apparatus, urodynamic

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or technical text with numerical values and abbreviations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.41
     also
    -1.35
     such
    -1.24
     that
    -1.17
     there
    -1.16
     their
    -1.13
     or
    -1.06
    だよね
    -1.03
    potensi
    -1.02
     which
    -1.01
    POSITIVE LOGITS
     perda
    1.05
     opulent
    1.02
     juxtaposition
    1.01
     Presidencia
    1.00
     unbelievably
    0.98
     сначала
    0.98
    дию
    0.98
     mercen
    0.96
     senin
    0.95
     ferrovia
    0.95
    Activations Density 0.012%

    No Known Activations