© 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. 34-GEMMASCOPE-RES-131K
    7. 78101
    Prev
    Next
    INDEX
    Explanations

    self- followed by a word

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

    This neuron detects words formed with the prefix “self-” (e.g., self-righteous, self-important, self-destructive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     точку
    -0.86
    trica
    -0.79
    тон
    -0.75
    pañas
    -0.73
    ダーク
    -0.72
     vermag
    -0.72
     جري
    -0.72
    偽
    -0.72
    紙
    -0.71
     другим
    -0.71
    POSITIVE LOGITS
     sabotage
    0.96
    destruct
    0.88
     inflicted
    0.84
    oudh
    0.82
     promoting
    0.82
    loginUser
    0.81
     absorbed
    0.81
     cinturón
    0.80
     sikker
    0.78
     focused
    0.78
    Activations Density 0.023%

    No Known Activations