© 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. 153812
    Prev
    Next
    INDEX
    Explanations

    directed affairs

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

    `let`, `Volumes`, `lineTo`, `elements`, `Message`

    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
    <unused1865>
    0.64
    ızlı
    0.58
    तिहासिक
    0.57
     пройти
    0.57
     arrivare
    0.56
    нэт
    0.55
    ൺലൈ
    0.54
    षिक
    0.53
     кг
    0.52
    稒
    0.52
    POSITIVE LOGITS
    0.52
    '
    0.52
    -
    0.50
     My
    0.48
     host
    0.48
     Mr
    0.47
     ‘
    0.47
     University
    0.46
     adoptive
    0.46
     Secretary
    0.46
    Activations Density 0.001%

    No Known Activations