© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5097
    Prev
    Next
    INDEX
    Explanations

    bracketed keywords or punctuation

    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
    n
    0.57
    t
    0.54
    et
    0.53
    el
    0.51
    ov
    0.44
    ש
    0.43
    er
    0.42
    u
    0.41
    M
    0.40
    it
    0.40
    POSITIVE LOGITS
    ного
    0.44
    ไม่ใช่
    0.43
    ीय
    0.39
     Pó
    0.38
    গতকাল
    0.37
     studente
    0.37
     personagem
    0.37
    ิน
    0.37
    ジェット
    0.37
    یان
    0.37
    Activations Density 0.000%

    No Known Activations