© 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. 128160
    Prev
    Next
    INDEX
    Explanations

    performing actions or skills

    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
     in
    -2.08
     by
    -1.55
    などと
    -1.45
     to
    -1.38
     鸟
    -1.23
    ousine
    -1.19
    ruguay
    -1.18
     or
    -1.17
    \,
    -1.16
    :
    -1.16
    POSITIVE LOGITS
     errone
    1.23
     farmacia
    1.23
     automatica
    1.22
     playera
    1.21
     busto
    1.20
     coster
    1.20
     quelqu
    1.20
    UNG
    1.19
     afirm
    1.17
    вості
    1.17
    Activations Density 0.055%

    No Known Activations