© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77121
    Prev
    Next
    INDEX
    Explanations

    yield return, Linoleic, Kiki, Twain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ides
    0.47
    and
    0.46
    /")
    0.45
    od
    0.43
    <0x00>
    0.41
    art
    0.41
     मोर्चा
    0.41
     SUM
    0.41
    muz
    0.41
    și
    0.40
    POSITIVE LOGITS
    見た
    0.49
    と比較
    0.46
    েনের
    0.44
    ベン
    0.44
    Phenyl
    0.44
    ргә
    0.44
    levelname
    0.44
    符合
    0.43
    鬣
    0.43
    ходили
    0.42
    Activations Density 0.005%

    No Known Activations