© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85682
    Prev
    Next
    INDEX
    Explanations

    made to

    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
     них
    -1.69
    昨日は
    -1.64
     masaj
    -1.64
     anonim
    -1.61
    ᨕ
    -1.56
    "])
    
    -1.52
    )
    
    -1.52
    ofed
    -1.52
     korrekt
    -1.48
     moldura
    -1.48
    POSITIVE LOGITS
     to
    3.06
     of
    2.31
     in
    2.23
     on
    2.16
    2
    1.88
     between
    1.78
    4
    1.77
     at
    1.72
     across
    1.69
     from
    1.68
    Activations Density 0.001%

    No Known Activations