© 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. 111016
    Prev
    Next
    INDEX
    Explanations

    action potentials

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

    technical identifiers in code and scientific literature, such as version numbers, project IDs, and scientific notation.

    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
     sig
    -0.72
    achy
    -0.70
     peut
    -0.68
     ouverte
    -0.67
    Launching
    -0.66
    cault
    -0.65
     сохра
    -0.65
    丧
    -0.64
     Sig
    -0.64
     avez
    -0.63
    POSITIVE LOGITS
     Granny
    0.76
    府
    0.74
     değ
    0.72
    量
    0.72
    望
    0.71
    音
    0.70
    香
    0.69
    酒店
    0.69
     dictionary
    0.69
    UID
    0.68
    Activations Density 0.079%

    No Known Activations