© 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. 34-GEMMASCOPE-RES-131K
    7. 63254
    Prev
    Next
    INDEX
    Explanations

    accessing by key

    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_34/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
    opie
    -0.97
    weaver
    -0.92
    unno
    -0.92
    nung
    -0.91
    fans
    -0.91
    を含
    -0.89
    maining
    -0.88
    などの
    -0.87
    hever
    -0.87
    bsen
    -0.84
    POSITIVE LOGITS
     key
    2.14
     getKey
    1.52
    Key
    1.52
     keys
    1.46
     Key
    1.41
    getKey
    1.37
    key
    1.35
     клю
    1.29
    KEY
    1.25
     clés
    1.15
    Activations Density 0.019%

    No Known Activations