© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42449
    Prev
    Next
    INDEX
    Explanations

    how to explain or prevent

    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
     fractal
    0.50
     brandy
    0.44
    Somos
    0.42
     polycarbonate
    0.41
     perennials
    0.41
    ᱷ
    0.40
     genus
    0.40
    鋰
    0.40
     avant
    0.39
     autonomía
    0.39
    POSITIVE LOGITS
    ைகள்
    0.48
     ”.
    0.46
    非
    0.45
    untuk
    0.44
    obes
    0.44
    userid
    0.44
     Liste
    0.44
    وري
    0.44
    setIs
    0.44
     subdue
    0.44
    Activations Density 0.004%

    No Known Activations