© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24899
    Prev
    Next
    INDEX
    Explanations

    code snippets and dates

    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_all/layer_41_width_262k_l0_big
    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
    🦵
    0.70
    .$,
    0.63
     harmonics
    0.60
    EARCH
    0.60
     solubility
    0.59
     anesthetic
    0.59
    .°
    0.57
    <unused1760>
    0.57
     datth
    0.56
    ্যান্স
    0.56
    POSITIVE LOGITS
    ar
    0.98
    er
    0.96
    an
    0.88
    o
    0.88
    u
    0.85
    i
    0.83
    1
    0.83
    ap
    0.81
    en
    0.78
    es
    0.76
    Activations Density 0.021%

    No Known Activations