© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11242
    Prev
    Next
    INDEX
    Explanations

    file path and type

    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
     from
    -1.34
     Préférences
    -0.99
    asst
    -0.94
     Exchanges
    -0.93
     espectáculo
    -0.93
    sct
    -0.92
    geology
    -0.92
     Needles
    -0.91
    conceito
    -0.90
     changes
    -0.90
    POSITIVE LOGITS
    woners
    1.05
    owska
    0.97
    }$,
    0.94
     andere
    0.94
    ,‎
    0.92
    usions
    0.91
    datable
    0.90
    ,
    0.90
    moiselle
    0.90
    kell
    0.89
    Activations Density 0.002%

    No Known Activations