© 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. 41283
    Prev
    Next
    INDEX
    Explanations

    beef

    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
     cercano
    2.05
    ਸ
    1.98
     semplici
    1.85
    ਮ
    1.84
    нг
    1.76
     geral
    1.76
    Sono
    1.76
    нде
    1.72
    ヤー
    1.71
     kecil
    1.70
    POSITIVE LOGITS
    s
    2.95
    ir
    2.67
    y
    2.66
    am
    2.17
    u
    2.16
    ad
    2.13
    ia
    1.97
    ים
    1.91
    ate
    1.88
    ের
    1.88
    Activations Density 0.002%

    No Known Activations