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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101947
    Prev
    Next
    INDEX
    Explanations

    finding informative content

    np_acts-logits-general · gemini-2.5-flash-lite

    links that shimmer and expand

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0.57
    -
    0.56
    ict
    0.51
     HM
    0.50
    or
    0.47
     Dict
    0.46
     DX
    0.46
    Dict
    0.45
    GD
    0.45
    DX
    0.45
    POSITIVE LOGITS
    زمانہ
    0.64
     sufrido
    0.60
     घेतला
    0.58
    ில்
    0.56
     میشود
    0.56
     سقوط
    0.55
    ≾
    0.55
     ہونے
    0.53
     تحلیل
    0.53
    زندگی
    0.53
    Activations Density 0.003%

    No Known Activations