© 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. 69866
    Prev
    Next
    INDEX
    Explanations

    fingers and their uses

    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
    </strong>
    -2.58
    ཫ
    -2.38
    bandicam
    -2.25
     fiore
    -2.14
    焿
    -2.13
    {
    -2.05
    螄
    -2.03
     anello
    -2.02
     وضعیت
    -2.02
     gefe
    -2.02
    POSITIVE LOGITS
     fingers
    2.81
     $
    2.78
     \&
    2.44
     $[
    2.42
    </td>
    2.38
     $(\
    2.33
     For
    2.31
    м
    2.30
     $\
    2.28
     From
    2.22
    Activations Density 0.001%

    No Known Activations