© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205511
    Prev
    Next
    INDEX
    Explanations

    melted ice

    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
    ?
    0.48
    !
    0.47
    le
    0.42
    ור
    0.42
     белән
    0.39
     ஏற்படுத்து
    0.39
     expensive
    0.39
    栅
    0.39
    窗
    0.39
    剂
    0.39
    POSITIVE LOGITS
    uberculosis
    0.52
     repaso
    0.50
     terrorist
    0.50
    gba
    0.48
    STORAGE
    0.48
    ّى
    0.48
    <unused44>
    0.48
    ust
    0.48
    anganese
    0.47
     मध्यप्रदेश
    0.47
    Activations Density 0.004%

    No Known Activations