© 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. 76255
    Prev
    Next
    INDEX
    Explanations

    biography section

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

    definitions and explanations

    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
    したが
    0.47
     оказалась
    0.44
    确实
    0.43
     \\
    0.41
    ிருந்த
    0.40
     разли
    0.39
    ");*/
    0.39
    しましたが
    0.39
    でしたが
    0.39
     notoriously
    0.39
    POSITIVE LOGITS
     objectif
    0.43
    ٹا
    0.43
     جسے
    0.42
    وری
    0.41
    گاه
    0.41
     mục
    0.41
     حصہ
    0.41
    Tribune
    0.41
    與
    0.41
     जिसे
    0.40
    Activations Density 0.000%

    No Known Activations