© 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. 23689
    Prev
    Next
    INDEX
    Explanations

    ICP, United States, Josh Stewart, October

    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
     tỉ
    -0.77
    toje
    -0.75
    昂
    -0.71
     pretending
    -0.68
    тье
    -0.68
    onaceous
    -0.68
     unat
    -0.68
    hedge
    -0.67
     tropical
    -0.67
    urai
    -0.66
    POSITIVE LOGITS
     Undead
    0.93
     ICP
    0.92
     CORP
    0.84
    masks
    0.82
     RZ
    0.79
     Beetle
    0.79
    eringen
    0.77
     Kandy
    0.76
    IPC
    0.75
    .}\
    0.75
    Activations Density 0.046%

    No Known Activations