© 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. 74896
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
     feront
    -2.09
     semelh
    -1.89
     devraient
    -1.84
     restent
    -1.82
     
    -1.78
    
    -1.77
    鶫
    -1.73
    kept
    -1.73
     deux
    -1.70
     alho
    -1.70
    POSITIVE LOGITS
     with
    2.42
     which
    2.20
     or
    2.09
     this
    2.05
     from
    1.99
     and
    1.94
     during
    1.89
     in
    1.79
    There
    1.76
     on
    1.75
    Activations Density 0.099%

    No Known Activations