© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41652
    Prev
    Next
    INDEX
    Explanations

    blindness, referral fee, nostrils, featuring, rendering, hosting, revolves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שלך
    0.80
    rando
    0.79
    сына
    0.77
     đáo
    0.70
    rze
    0.69
     ਦੇ
    0.68
     قاسمی
    0.68
    ﺭ
    0.68
    ETTE
    0.67
     উহার
    0.66
    POSITIVE LOGITS
    ല
    0.84
    するには
    0.79
    することは
    0.79
    俩
    0.79
    மதி
    0.78
     partage
    0.77
     smuggling
    0.77
     Economía
    0.77
     recherche
    0.77
     entretenimiento
    0.77
    Activations Density 0.000%

    No Known Activations