© 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. 40942
    Prev
    Next
    INDEX
    Explanations

    adding creativity and touch

    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
    ات
    0.93
     Large
    0.93
     যাইহোক
    0.84
    s
    0.84
     Behavioral
    0.82
    degenerative
    0.80
     フロ
    0.79
     dilatation
    0.77
    クレジット
    0.77
     behavioral
    0.76
    POSITIVE LOGITS
    dır
    0.90
    imab
    0.82
    电线路
    0.82
    yer
    0.81
    도는
    0.80
    랑
    0.79
    iyah
    0.79
    esome
    0.79
    ONOM
    0.78
    zerel
    0.78
    Activations Density 0.000%

    No Known Activations