© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57454
    Prev
    Next
    INDEX
    Explanations

    medical pain relief

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

    formatting patterns like section headers, tags, and structural elements in 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
    autres
    -0.88
     pflegen
    -0.87
    ácie
    -0.83
    Ново
    -0.81
    _${
    -0.80
     patter
    -0.80
    ڠ
    -0.79
     Giga
    -0.79
     BER
    -0.78
    typec
    -0.77
    POSITIVE LOGITS
     sfondo
    0.89
     csapat
    0.88
     Jwt
    0.87
     stesse
    0.81
     большин
    0.78
    ffè
    0.77
    solicitud
    0.77
     addirittura
    0.75
    etah
    0.75
     somehow
    0.75
    Activations Density 0.004%

    No Known Activations