© 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. 207307
    Prev
    Next
    INDEX
    Explanations

    actually have, without giving, ten children, no charges

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

    initiating descriptive clauses

    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
    𝙶
    0.57
     Palaiseau
    0.52
    人事
    0.50
    ርዓ
    0.48
     Corolle
    0.48
     зала
    0.48
    (|
    0.48
    𝗡
    0.47
    }^{(\
    0.47
    ानंद
    0.46
    POSITIVE LOGITS
     dezembro
    0.50
    wink
    0.48
    ốn
    0.47
     في
    0.47
     Elevated
    0.46
     elevated
    0.46
    d
    0.46
     amp
    0.45
     android
    0.44
     AMP
    0.44
    Activations Density 0.001%

    No Known Activations