© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9748
    Prev
    Next
    INDEX
    Explanations

    mind followed by fulness or set

    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
    TH
    1.78
    Te
    1.77
    MER
    1.70
    dozen
    1.66
    TE
    1.64
    TEST
    1.63
    BAR
    1.63
    ä
    1.63
    EE
    1.59
    º
    1.59
    POSITIVE LOGITS
    та
    3.03
    𝓮
    2.61
    ли
    2.55
    ف
    2.38
    ம்
    2.34
    𝓵
    2.31
    ྂ
    2.31
    といった
    2.28
    ك
    2.22
    𝓪
    2.22
    Activations Density 0.036%

    No Known Activations