© 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. 93924
    Prev
    Next
    INDEX
    Explanations

    public domain, policy, defender, health

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

    terms related to government or public institutions, particularly in legal contexts.

    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
     listen
    -0.74
    pope
    -0.72
    isNotBlank
    -0.71
     direttore
    -0.70
     auttaa
    -0.69
     Listen
    -0.68
     apunta
    -0.68
    Listen
    -0.67
    年から
    -0.65
    אבל
    -0.65
    POSITIVE LOGITS
    Matrix
    0.82
     convenience
    0.82
     mett
    0.81
    iot
    0.76
    ólica
    0.76
     Taran
    0.76
    的道
    0.74
     prints
    0.73
    Convenience
    0.73
     MATRIX
    0.73
    Activations Density 0.024%

    No Known Activations