© 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. 39821
    Prev
    Next
    INDEX
    Explanations

    compound names

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

    variable assignments in programming code where a variable is set to a value.

    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
     can
    -1.53
     at
    -1.41
    Szia
    -1.30
    pulseira
    -1.30
     iNdEx
    -1.28
    !(:
    -1.27
    replyreport
    -1.27
    uspiel
    -1.21
    見て
    -1.20
    gorro
    -1.20
    POSITIVE LOGITS
    没有人
    1.27
    毎回
    1.22
    鼯
    1.16
    鶺
    1.16
     Mascara
    1.15
     batterie
    1.14
     EPISODE
    1.13
     bateria
    1.13
     Personas
    1.13
     ILLINOIS
    1.11
    Activations Density 0.006%

    No Known Activations