© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    not self, technical terms

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

    The neuron fires on isolated technical identifiers—uppercase acronyms, code symbols, compiler directives, and other programming‐style tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -1.49
     which
    -1.16
     instead
    -1.13
    hütte
    -1.12
    áska
    -1.09
    ummings
    -1.08
    CCIÓN
    -1.06
    Boxscore
    -1.05
     梁
    -1.05
     precisam
    -1.05
    POSITIVE LOGITS
    still
    1.31
    descri
    1.30
    offers
    1.21
    due
    1.21
     nor
    1.21
     to
    1.20
    continue
    1.18
    begins
    1.18
    ่าน
    1.15
    allows
    1.14
    Activations Density 0.196%

    No Known Activations