© 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. 111935
    Prev
    Next
    INDEX
    Explanations

    months, resources, popup, distance, blank

    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
    󠁣
    0.45
    گ
    0.44
    chetto
    0.43
    대를
    0.42
     ഉയർന്ന
    0.42
     erhö
    0.42
    ロ
    0.41
    人员
    0.41
    殊
    0.41
    ро
    0.41
    POSITIVE LOGITS
     poop
    0.49
     extenso
    0.47
     иностран
    0.46
    付款
    0.46
     rekla
    0.45
     представ
    0.45
     swabs
    0.45
     воск
    0.45
    OLA
    0.44
     пар
    0.44
    Activations Density 0.002%

    No Known Activations