© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226549
    Prev
    Next
    INDEX
    Explanations

    Miniatures Fair, begin with G, effort yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    だ
    0.44
    ("#
    0.43
    UPLOAD
    0.43
    મના
    0.41
    <0x89>
    0.40
    Insertion
    0.40
    Thailand
    0.40
    ඪ
    0.39
    Wrong
    0.39
    Upload
    0.38
    POSITIVE LOGITS
     مخت
    0.47
     Verlust
    0.47
     decommission
    0.46
     miał
    0.46
     pener
    0.46
     നിന്നും
    0.46
     Vereinig
    0.45
     mooi
    0.45
     розподі
    0.45
     depreciation
    0.45
    Activations Density 0.001%

    No Known Activations