© 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. 22-GEMMASCOPE-RES-131K
    7. 25511
    Prev
    Next
    INDEX
    Explanations

    CCCC and C9

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

    This neuron detects the uppercase sequence “PWN” (and its sub-components like “PW” or “WN”), i.e. the PWN header abbreviation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.13
    armani
    -1.09
     and
    -1.09
    türk
    -1.08
    harmed
    -1.07
    embro
    -1.03
     decreases
    -1.02
    ⿰
    -1.02
    farol
    -1.02
     decreased
    -1.02
    POSITIVE LOGITS
    まずは
    1.23
     walmart
    1.20
    a
    1.16
    8
    1.16
    c
    1.15
    u
    1.08
    y
    1.07
    ara
    1.05
    no
    1.05
    am
    1.04
    Activations Density 0.008%

    No Known Activations