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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109730
    Prev
    Next
    INDEX
    Explanations

    magick, yea, and then store

    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_40_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
    s
    0.59
    a
    0.56
    “
    0.55
     has
    0.54
    an
    0.52
     a
    0.51
     to
    0.51
    at
    0.49
    et
    0.48
     the
    0.48
    POSITIVE LOGITS
    ijnlijk
    0.57
    ქვენ
    0.53
    )}\
    0.46
    👄
    0.46
    르
    0.46
     ं
    0.45
    溫度
    0.45
     등
    0.44
    .}\
    0.44
    𝟑
    0.44
    Activations Density 0.224%

    No Known Activations