© 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. 35482
    Prev
    Next
    INDEX
    Explanations

    onClick handlers

    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
    С
    1.56
    एसआई
    1.55
    𝘽
    1.47
    rbara
    1.39
    ać
    1.38
    ынша
    1.37
    eal
    1.35
    deki
    1.32
    ESOME
    1.32
    semantics
    1.31
    POSITIVE LOGITS
    ل
    2.70
    ро
    2.02
    ли
    1.97
    ور
    1.88
    л
    1.78
    ва
    1.76
    ა
    1.73
    т
    1.72
    ка
    1.71
    ст
    1.69
    Activations Density 0.005%

    No Known Activations