© 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. 106552
    Prev
    Next
    INDEX
    Explanations

    chapter or section titles

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

    introduction and foundations

    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
    鴎
    0.45
    (),
    0.44
     אם
    0.42
     є
    0.42
    agor
    0.41
    積極的に
    0.41
    ጐ
    0.40
    事で
    0.39
    ?,
    0.39
    Ӯ
    0.39
    POSITIVE LOGITS
     comien
    0.50
     Sailing
    0.45
     paisajes
    0.44
     Introduction
    0.44
     Einführung
    0.43
     Launch
    0.43
     Prolog
    0.43
     introduction
    0.42
     introdu
    0.42
     flancs
    0.42
    Activations Density 0.000%

    No Known Activations