© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30276
    Prev
    Next
    INDEX
    Explanations

    assembly or medical conditions

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

    auto-generated code comments warning about not modifying a file.

    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
     your
    -0.84
    prete
    -0.83
    barco
    -0.81
     cross
    -0.81
     other
    -0.81
    preso
    -0.79
     instituciones
    -0.79
    lente
    -0.77
    institutions
    -0.77
     coisa
    -0.77
    POSITIVE LOGITS
    assembly
    0.86
    мана
    0.81
     Assembly
    0.81
     section
    0.79
    IC
    0.78
     syd
    0.76
    Assembly
    0.76
     componen
    0.75
     tresses
    0.74
    TP
    0.74
    Activations Density 0.004%

    No Known Activations