© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41451
    Prev
    Next
    INDEX
    Explanations

    Carmen Electra, Halle in, Glitter Band, Scorpion ARMS

    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
     Also
    -2.75
     However
    -2.48
    ل
    -2.44
     ก็
    -2.38
     It
    -2.33
     admirable
    -2.30
    籥
    -2.27
     lösen
    -2.25
    臾
    -2.22
     fühlen
    -2.20
    POSITIVE LOGITS
    the
    3.06
    k
    2.94
    d
    2.91
    s
    2.86
    wheres
    2.59
     sii
    2.56
    e
    2.56
    to
    2.50
    哢
    2.48
     sosis
    2.45
    Activations Density 0.004%

    No Known Activations