© 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. 34-GEMMASCOPE-RES-131K
    4. 98385
    Prev
    Next
    INDEX
    Explanations

    phrase starters

    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_34/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
     Provinsi
    -0.97
     sorprende
    -0.85
    κου
    -0.78
    Boxscore
    -0.73
     Código
    -0.73
    ניות
    -0.73
    Monsters
    -0.73
     planea
    -0.72
    Azur
    -0.70
     Nä
    -0.70
    POSITIVE LOGITS
     almeno
    0.81
     בש
    0.76
     boc
    0.75
    sia
    0.75
     Jeb
    0.72
    *-
    0.71
    Cleveland
    0.70
     afore
    0.69
    ropical
    0.69
    Ary
    0.69
    Activations Density 0.013%

    No Known Activations