© 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. 41727
    Prev
    Next
    INDEX
    Explanations

    grated/shredded and accompaniments

    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
    ли
    1.71
    ن
    1.46
    ला
    1.37
     желание
    1.27
     Besonders
    1.22
    吗
    1.19
     Trebuie
    1.18
     quieras
    1.12
     Stunning
    1.09
    来て
    1.09
    POSITIVE LOGITS
    dır
    1.54
    mdash
    1.16
    der
    1.16
    gies
    1.12
    ndash
    1.11
    മതി
    1.11
    gister
    1.08
    дування
    1.07
    δοση
    1.06
    g
    1.05
    Activations Density 0.021%

    No Known Activations