© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    dialectical, inductive, fracture, convection, tectonics

    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
    ق
    3.19
    س
    2.81
    てる
    2.61
    с
    2.61
    ج
    2.59
    га
    2.45
    ма
    2.33
    ع
    2.33
    িক
    2.30
    きました
    2.30
    POSITIVE LOGITS
    ić
    2.98
    ை
    2.89
    le
    2.52
    ı
    2.36
    ya
    2.34
    aa
    2.30
    iu
    2.27
    iw
    2.25
    zak
    2.22
    ıya
    2.22
    Activations Density 0.069%

    No Known Activations