© 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. 14917
    Prev
    Next
    INDEX
    Explanations

    disabled, defeated, or removed

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

    The neuron fires on strong transitive verbs that denote forcibly disabling, neutralizing, or “taking out” a target.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     gela
    -1.56
     lokale
    -1.48
     maske
    -1.45
     ekst
    -1.45
     eier
    -1.45
     ;-
    -1.42
     ideen
    -1.42
     kontrak
    -1.41
     gik
    -1.41
     uly
    -1.40
    POSITIVE LOGITS
     με
    1.70
     With
    1.67
     by
    1.64
     Several
    1.44
     visión
    1.38
     visão
    1.38
     Most
    1.37
     dengan
    1.32
     a
    1.32
    bliž
    1.29
    Activations Density 0.037%

    No Known Activations