© 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. 81485
    Prev
    Next
    INDEX
    Explanations

    ACP or CP variations

    np_acts-logits-general · gemini-2.5-flash-lite

    character encoding specifications, particularly Windows-1252 encoding.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    pesas
    -0.79
     congress
    -0.75
     Gwen
    -0.74
    Erfolge
    -0.73
     رہ
    -0.73
     nurse
    -0.71
    enviar
    -0.71
    bánh
    -0.69
    部位
    -0.69
    สัง
    -0.68
    POSITIVE LOGITS
    ACP
    1.05
    Cp
    0.98
     cp
    0.97
     CP
    0.97
    CP
    0.96
     ACP
    0.90
     page
    0.90
    page
    0.88
    acp
    0.87
     Cp
    0.86
    Activations Density 0.033%

    No Known Activations