© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72186
    Prev
    Next
    INDEX
    Explanations

    science, biology, and division

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

    scientific or technical terms in academic or research texts.

    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
     and
    -2.53
    หรือ
    -1.41
     boîtier
    -1.38
     or
    -1.34
     jednod
    -1.27
    และ
    -1.26
     różnych
    -1.26
     또
    -1.25
     chargeur
    -1.22
     ganchillo
    -1.21
    POSITIVE LOGITS
     «
    1.38
    -
    1.29
     of
    1.20
     ‘‘
    1.15
    !
    1.09
    ;
    1.06
    ~
    1.05
    _
    1.05
    gs
    1.03
    ők
    1.02
    Activations Density 0.109%

    No Known Activations