© 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. 40650
    Prev
    Next
    INDEX
    Explanations

    many people

    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
    or
    1.33
    IS
    1.29
    id
    1.26
    art
    1.23
    ح
    1.22
    RES
    1.21
    leger
    1.20
    ot
    1.17
     or
    1.14
     on
    1.11
    POSITIVE LOGITS
    ა
    1.84
    ১০
    1.55
    ان
    1.46
    𝙤
    1.45
    ⠑
    1.44
    ∑</
    1.42
     ہے۔
    1.41
    DataXYZ
    1.41
    𝙚
    1.39
    浧
    1.35
    Activations Density 0.011%

    No Known Activations