© 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. 11332
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    al
    2.09
    م
    1.99
    it
    1.71
    و
    1.69
    ot
    1.68
    м
    1.66
    g
    1.63
    ar
    1.62
    y
    1.61
    ו
    1.59
    POSITIVE LOGITS
    In
    1.66
    ęs
    1.66
    ă
    1.66
    ęcia
    1.61
    ąda
    1.58
    tees
    1.57
    Dropped
    1.57
    棪
    1.55
     personer
    1.51
    에
    1.49
    Activations Density 0.081%

    No Known Activations