© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1617
    Prev
    Next
    INDEX
    Explanations

    regardless, specified, way, converted, believes

    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_31_width_16k_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
    /
    0.85
    ？）
    0.73
    ራል
    0.72
    ናል
    0.71
    ጣል
    0.71
    Для
    0.70
    FilesIn
    0.70
     untuk
    0.69
    ပါတယ်
    0.68
    "/"
    0.68
    POSITIVE LOGITS
    ។
    1.88
    。
    1.62
    ™.
    1.59
    ®.
    1.57
    ۔
    1.56
    °.
    1.52
     ذریع
    1.51
    ).
    1.48
    }.
    1.41
    ³.
    1.41
    Activations Density 0.015%

    No Known Activations