© 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. 248134
    Prev
    Next
    INDEX
    Explanations

    common method, managers in, descriptive elaboration

    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
     را
    0.49
     realise
    0.47
     konstru
    0.47
     tribu
    0.47
     മുതല്‍
    0.46
     ноября
    0.46
     촉
    0.46
     ሕ
    0.45
     Haziran
    0.44
     партії
    0.44
    POSITIVE LOGITS
    olate
    0.51
    و
    0.51
    дра
    0.49
    y
    0.48
    ยา
    0.48
    ภัย
    0.47
    robat
    0.46
    طيب
    0.46
    λιο
    0.46
    رب
    0.46
    Activations Density 0.000%

    No Known Activations