© 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. 22-GEMMASCOPE-RES-131K
    7. 16241
    Prev
    Next
    INDEX
    Explanations

    entities and groups

    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_22/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
    Whilst
    -1.04
     Whilst
    -0.98
    Ȧ
    -0.98
    respective
    -0.96
     jedoch
    -0.96
     garner
    -0.95
     економі
    -0.94
    
    -0.93
    bangunan
    -0.93
    வில்
    -0.93
    POSITIVE LOGITS
     renda
    1.04
    έ
    1.04
    :"",
    0.97
    <<<<<<<
    0.96
     և
    0.96
     cioè
    0.95
    editMode
    0.94
     extremely
    0.94
    Procedimento
    0.94
     merupakan
    0.94
    Activations Density 0.060%

    No Known Activations