© 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. 75794
    Prev
    Next
    INDEX
    Explanations

    xe2x80x9cbladedxe2x80x9d, xe2x80x9cvirusxe2x80x9d, xe2x80x9cairbag cushion,xe2x80x9d

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

    HTML tags or encoding markers within technical documents.

    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
     really
    -0.99
     with
    -0.87
     Often
    -0.86
     an
    -0.85
     With
    -0.84
     made
    -0.81
     often
    -0.81
     almost
    -0.81
     on
    -0.79
    وفر
    -0.79
    POSITIVE LOGITS
     DIFFERENT
    0.98
     PROCEDURE
    0.98
    gebracht
    0.96
     postale
    0.95
    female
    0.95
    leitung
    0.95
     Coimbatore
    0.95
     FOLLOWING
    0.94
     UNIVERSITY
    0.92
     oe
    0.92
    Activations Density 0.016%

    No Known Activations