© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13564
    Prev
    Next
    INDEX
    Explanations

    cancer risk

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

    titles of academic or scientific articles, particularly focusing on the colon after the title topic.

    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_10/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
    鬭
    -1.25
     were
    -1.24
    forgettable
    -1.23
    ERON
    -1.23
    complicated
    -1.16
    columnHeader
    -1.13
    wonderful
    -1.13
     and
    -1.08
    ANDS
    -1.08
     *}$
    -1.07
    POSITIVE LOGITS
     (
    1.30
    Spesifikasi
    1.16
     only
    1.16
     different
    1.14
     stricter
    1.12
     its
    1.11
     dalamnya
    1.09
    Гор
    1.09
     shaky
    1.08
    deauna
    1.08
    Activations Density 0.136%

    No Known Activations