© 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. 35697
    Prev
    Next
    INDEX
    Explanations

    FDM

    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
     मजा
    1.52
    젹
    1.49
    го
    1.48
    grund
    1.41
    ремя
    1.40
    ESOME
    1.40
     connotation
    1.37
     appendices
    1.34
     शेखर
    1.30
     décrites
    1.30
    POSITIVE LOGITS
    ان
    2.00
    ed
    1.91
    el
    1.84
    an
    1.79
    en
    1.70
    zinho
    1.69
    на
    1.63
    ל
    1.61
    on
    1.58
    '
    1.57
    Activations Density 0.002%

    No Known Activations