© 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. 34-GEMMASCOPE-RES-131K
    7. 108857
    Prev
    Next
    INDEX
    Explanations

    a description or identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Municipalidad
    -1.26
    flowing
    -1.20
     lorsque
    -1.16
    ㈯
    -1.14
    eronau
    -1.11
    (=)
    -1.10
     PROBLE
    -1.09
     ľudí
    -1.09
    垪
    -1.08
    populated
    -1.07
    POSITIVE LOGITS
     a
    2.83
     from
    2.44
     an
    2.03
     in
    1.53
     on
    1.34
     also
    1.24
     seorang
    1.21
     gay
    1.13
     undead
    1.11
     part
    1.05
    Activations Density 0.097%

    No Known Activations