© 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. 102845
    Prev
    Next
    INDEX
    Explanations

    URLs and links

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

    ellipses or trailing punctuation (like "...") that indicate incomplete thoughts or continuation, particularly in technical or conversational 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
    A
    -2.77
    \
    -2.48
    ſtra
    -2.41
    一個
    -2.38
    涐
    -2.33
    ！！！！
    -2.20
    :
    -2.16
    ”;
    -2.06
    Étape
    -2.05
     and
    -2.02
    POSITIVE LOGITS
     They
    3.55
    …"
    3.25
    TintMode
    2.83
    wickshire
    2.80
     Tieren
    2.67
    乆
    2.53
    癀
    2.48
    ி
    2.47
     Similarly
    2.45
    re
    2.44
    Activations Density 0.005%

    No Known Activations