© 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. 12-GEMMASCOPE-2-RES-262K
    7. 37434
    Prev
    Next
    INDEX
    Explanations

    writing to

    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
    ভাবে
    1.58
    ों
    1.57
    מ
    1.52
    s
    1.38
    ের
    1.38
    strukt
    1.35
    Ве
    1.34
    ために
    1.31
    にする
    1.30
    過ご
    1.30
    POSITIVE LOGITS
    o
    1.73
    ﻛ
    1.56
    in
    1.52
    ü
    1.48
    lardı
    1.43
    e
    1.39
    manship
    1.35
    mals
    1.34
    tyle
    1.34
    m
    1.30
    Activations Density 0.002%

    No Known Activations