© 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. 57738
    Prev
    Next
    INDEX
    Explanations

    Copyright and legal symbols

    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
     Verbs
    -0.77
    有时候
    -0.76
    USER
    -0.76
     calavera
    -0.75
     يه
    -0.75
     Murillo
    -0.75
     Miquel
    -0.75
    navigationItem
    -0.74
    Virgin
    -0.73
     Barriers
    -0.72
    POSITIVE LOGITS
    洋服
    0.77
    慵
    0.74
     ••
    0.73
     batter
    0.68
    rmk
    0.66
    Doubt
    0.66
    Batter
    0.65
    投げ
    0.64
    ères
    0.64
    skills
    0.64
    Activations Density 0.020%

    No Known Activations