© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7533
    Prev
    Next
    INDEX
    Explanations

    symbols and lists

    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
     adheres
    0.77
    可
    0.77
    𝘥
    0.76
    pineapple
    0.76
     nourishing
    0.75
    ⊹
    0.74
    mutable
    0.73
     undertakes
    0.73
     partake
    0.71
    ㄓ
    0.71
    POSITIVE LOGITS
    ål
    0.69
    änner
    0.68
     Kör
    0.68
    ür
    0.68
    ê
    0.66
    ïde
    0.66
     vrouwen
    0.66
    ارق
    0.64
     Ö
    0.64
    ITER
    0.64
    Activations Density 0.000%

    No Known Activations