© 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. 154747
    Prev
    Next
    INDEX
    Explanations

    tax-exempt bond proceeds training

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

    historically, contrasted with current methods

    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
    rizes
    0.47
    られた
    0.46
    ol
    0.45
    रोला
    0.44
    Greece
    0.44
    帮
    0.43
    WD
    0.42
    GetMapping
    0.42
    skyblue
    0.42
    reve
    0.42
    POSITIVE LOGITS
     政府
    0.50
     audioElement
    0.44
     unamb
    0.41
     Теннис
    0.41
    🎙
    0.41
     is
    0.40
     عليه
    0.40
     virtu
    0.40
     સરકાર
    0.40
     Intelligent
    0.40
    Activations Density 0.000%

    No Known Activations