© 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. 102633
    Prev
    Next
    INDEX
    Explanations

    code comments, special characters, and mathematics

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

    words starting with the letter "P" (or "П" in Cyrillic) at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    0
    -2.70
    ↵↵
    -2.53
     \
    -2.42
     kleines
    -2.20
     improbable
    -2.13
     moody
    -2.05
     unhappy
    -2.02
    惴
    -1.99
    蝗
    -1.99
     nuestras
    -1.97
    POSITIVE LOGITS
    the
    3.58
    柃
    2.48
    \
    2.44
    atively
    2.27
    gemaakt
    2.23
     éclairage
    2.23
    从中
    2.19
    м
    2.19
    塒
    2.16
     vair
    2.14
    Activations Density 0.002%

    No Known Activations