© 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. 127652
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    </u>
    -2.08
    just
    -2.02
     those
    -1.79
    </strong>
    -1.76
     on
    -1.69
     garner
    -1.63
     additional
    -1.63
     as
    -1.61
     impeccable
    -1.59
     dozens
    -1.58
    POSITIVE LOGITS
    ᚔ
    1.98
     acclaimed
    1.98
    ፨
    1.96
    苤
    1.94
     exceedingly
    1.88
     lauded
    1.88
     VERY
    1.81
    ⢪
    1.80
     trouvé
    1.79
     необходимо
    1.77
    Activations Density 0.011%

    No Known Activations