© 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. 76395
    Prev
    Next
    INDEX
    Explanations

    state university college

    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
    enty
    -0.72
    HEET
    -0.71
    unca
    -0.71
    Projected
    -0.70
     Descriptors
    -0.69
    мула
    -0.69
     Falmouth
    -0.68
     Pilate
    -0.68
    hæng
    -0.68
     Greer
    -0.65
    POSITIVE LOGITS
     OSU
    1.00
     Guelph
    0.94
    Manhattan
    0.90
    MSU
    0.89
    OSU
    0.84
     Veterinary
    0.83
     MSU
    0.83
     Agg
    0.83
     veterinary
    0.82
    ISU
    0.82
    Activations Density 0.049%

    No Known Activations