© 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. 74112
    Prev
    Next
    INDEX
    Explanations

    a noun/adjective

    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
    </em>
    -1.44
     silicona
    -1.40
     駅前
    -1.38
     considerando
    -1.35
    态度
    -1.34
    の前に
    -1.32
     voordat
    -1.32
    蟳
    -1.31
    合って
    -1.31
     envo
    -1.31
    POSITIVE LOGITS
     of
    2.94
     such
    1.77
    7
    1.75
    </h1>
    1.70
    providedIn
    1.68
     {
    1.66
     them
    1.63
    :
    1.58
    );
    1.57
     już
    1.57
    Activations Density 0.024%

    No Known Activations