© 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. 10-GEMMASCOPE-RES-131K
    7. 128308
    Prev
    Next
    INDEX
    Explanations

    scorpion, corpions, Scor, scorch,ipede, AD, Scorable

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

    biological and scientific terms related to scorpions, arthropods, and similar creatures.

    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
    蹓
    -2.39
    ндарт
    -2.30
    ꯸
    -2.23
    ть
    -2.08
    اں
    -2.02
    螓
    -2.02
    zers
    -2.00
    lossians
    -1.98
    pped
    -1.96
    ssystem
    -1.95
    POSITIVE LOGITS
    ↵
    2.88
    </h2>
    2.72
     speziellen
    2.39
     realizará
    2.20
    $,
    2.14
     starken
    2.00
    at
    1.98
     has
    1.98
     laaj
    1.93
    手掌
    1.92
    Activations Density 0.005%

    No Known Activations