© 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. 112995
    Prev
    Next
    INDEX
    Explanations

    gut net neutrality

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

    the word "gut" and its variants (gutted, guts, gutsy) in various 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
     Hinblick
    -2.63
     selben
    -2.42
    旆
    -2.33
    舠
    -2.28
    鮰
    -2.25
    of
    -2.23
     MISCELLANEOUS
    -2.16
    ୮
    -2.13
    棪
    -2.13
    e
    -2.11
    POSITIVE LOGITS
     atau
    2.39
    蚕
    2.28
    遢
    2.11
    是非常
    2.09
    ↵
    2.08
    fficking
    2.08
    ৭
    2.06
     pleas
    2.06
     nourishing
    2.02
     gutted
    1.98
    Activations Density 0.007%

    No Known Activations