© 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. 113266
    Prev
    Next
    INDEX
    Explanations

    SQlite, RCA, JPG, SMA

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

    the token "SQ" appearing in technical or code contexts, particularly in database-related content (SQLite) and abbreviated terms (like RCA in medical/technical contexts).

    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
    
    -2.50
    BITDA
    -2.42
     tetapi
    -2.31
     水彩
    -2.30
    ﮯ
    -2.28
    capacete
    -2.27
    )”
    -2.23
     rapido
    -2.17
     Miß
    -2.16
    蚨
    -2.16
    POSITIVE LOGITS
    on
    3.00
    er
    3.00
     theres
    2.45
    ,"
    2.33
    "
    2.30
    F
    2.30
    B
    2.28
     prefers
    2.23
     /
    2.16
     到着
    2.09
    Activations Density 0.004%

    No Known Activations