© 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. 40929
    Prev
    Next
    INDEX
    Explanations

    fill out

    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
    {
    1.24
     руках
    1.18
    레스
    1.16
     少し
    1.16
    Π
    1.15
    시대
    1.14
    𝐼
    1.14
    ới
    1.12
    AK
    1.11
    ו
    1.11
    POSITIVE LOGITS
    га
    1.67
    та
    1.59
    т
    1.54
    дные
    1.51
    ло
    1.32
    стые
    1.26
    ಗೊಳ
    1.26
    тный
    1.25
    ний
    1.23
    ació
    1.23
    Activations Density 0.002%

    No Known Activations