© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99257
    Prev
    Next
    INDEX
    Explanations

    Specific initial letters followed by specific continuations

    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
    紀錄
    -0.79
    遂
    -0.73
     Fletcher
    -0.71
     prophylaxis
    -0.71
     Acharya
    -0.71
     seals
    -0.71
    ījum
    -0.70
    вете
    -0.69
     pequenas
    -0.67
    にゃ
    -0.67
    POSITIVE LOGITS
    market
    0.85
     market
    0.84
    знес
    0.83
     Magist
    0.81
    Passengers
    0.77
     odio
    0.75
    rste
    0.75
     magist
    0.73
     sepul
    0.73
     exerc
    0.72
    Activations Density 0.021%

    No Known Activations