© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50095
    Prev
    Next
    INDEX
    Explanations

    variable names and assignments

    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
     muszą
    -0.85
     entgegen
    -0.82
     subgoals
    -0.81
     Then
    -0.77
     близько
    -0.76
     市場
    -0.76
     annehmen
    -0.75
     them
    -0.75
     Compulsory
    -0.75
    vellous
    -0.74
    POSITIVE LOGITS
    ʺ
    0.89
     "";
    0.89
    fő
    0.88
    僵
    0.82
    vatar
    0.81
     '';
    0.81
    ེ་
    0.80
    ｓ
    0.80
    ENTES
    0.79
     banget
    0.79
    Activations Density 0.000%

    No Known Activations