© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150664
    Prev
    Next
    INDEX
    Explanations

    insulted words

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

    initial probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grafik
    0.50
     mangiare
    0.50
    爺
    0.50
     graphique
    0.48
     dessins
    0.47
     graphics
    0.46
    ד
    0.46
     horaires
    0.46
     permettant
    0.46
     miei
    0.46
    POSITIVE LOGITS
     insulted
    0.46
    )_\
    0.45
    ベント
    0.44
     थाने
    0.44
    insulated
    0.44
     showered
    0.43
     cated
    0.43
    )_{(
    0.42
     insulting
    0.42
     स्वाभाविक
    0.41
    Activations Density 0.001%

    No Known Activations