© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93201
    Prev
    Next
    INDEX
    Explanations

    Hø, Gö, Kör prefixes

    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
    Inappropriate
    -0.78
    ㄕ
    -0.75
     BRA
    -0.75
    ニーズ
    -0.73
     générale
    -0.72
     Joss
    -0.71
    
    -0.71
    ớm
    -0.70
     維
    -0.68
    lyte
    -0.68
    POSITIVE LOGITS
     pięk
    0.77
    heard
    0.77
    वे
    0.74
     Gemüse
    0.70
    llen
    0.70
    Banyak
    0.69
     SHOW
    0.69
    ear
    0.67
     Kartoff
    0.67
     nampak
    0.67
    Activations Density 0.025%

    No Known Activations