© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    brilliant adjective

    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
    я
    2.08
    ar
    2.02
    ться
    2.00
    على
    1.98
    ת
    1.94
     ovvero
    1.88
    ної
    1.86
    ać
    1.81
    ação
    1.80
    یت
    1.80
    POSITIVE LOGITS
    ρα
    1.97
    ᴅ
    1.71
    它
    1.62
     scorn
    1.60
    ကြောင့်
    1.59
     gên
    1.59
    垲
    1.56
    DN
    1.55
    stricken
    1.55
     उन्मूलन
    1.54
    Activations Density 0.008%

    No Known Activations