© 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. 40742
    Prev
    Next
    INDEX
    Explanations

    software and requirements

    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
    ak
    1.63
    ن
    1.53
    ди
    1.51
    ce
    1.50
    te
    1.45
    ac
    1.38
    نیم
    1.37
    椃
    1.37
    αν
    1.31
    ic
    1.30
    POSITIVE LOGITS
    م
    1.43
    ため
    1.40
    СТ
    1.39
     permitting
    1.28
    ٌ
    1.28
     hunk
    1.26
     eponymous
    1.23
    CES
    1.21
    মতী
    1.21
     الاعزاء
    1.20
    Activations Density 0.001%

    No Known Activations