© 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. 10-GEMMASCOPE-RES-131K
    7. 14225
    Prev
    Next
    INDEX
    Explanations

    describing careers

    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_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
    urgery
    -1.27
    ژی
    -1.26
    Kemudian
    -1.23
    is
    -1.20
     on
    -1.18
     poème
    -1.18
    us
    -1.17
    Tetapi
    -1.16
    result
    -1.16
     intval
    -1.12
    POSITIVE LOGITS
     its
    1.70
     abbildung
    1.34
     to
    1.20
     of
    1.19
    在那里
    1.17
    umerable
    1.15
    ñado
    1.14
    ffl
    1.14
    那里
    1.14
     how
    1.14
    Activations Density 0.060%

    No Known Activations