© 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. 22-GEMMASCOPE-RES-131K
    7. 65776
    Prev
    Next
    INDEX
    Explanations

    chemical names with hyphens

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

    numeric values in chemical compound structures or formulas.

    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_22/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
    ほんとに
    -1.13
    樒
    -1.11
    又一次
    -1.05
     حتی
    -1.04
     ۱۳۹
    -1.04
    比起
    -1.03
    驚く
    -1.03
     nawet
    -1.03
    ViewFeatures
    -1.02
     ۱۲
    -1.02
    POSITIVE LOGITS
    האם
    1.20
    ஒ
    1.02
    视着
    1.02
    también
    0.95
    sianic
    0.94
     leave
    0.92
     ochi
    0.91
    איך
    0.91
     Abroad
    0.91
     another
    0.91
    Activations Density 0.056%

    No Known Activations