© 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. 181240
    Prev
    Next
    INDEX
    Explanations

    edited steps to reproduce

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

    ultimate goal of pleasure

    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
     humanist
    0.53
    难以
    0.52
     kehidupan
    0.48
     veracity
    0.48
    elten
    0.47
     شادی
    0.46
     reflector
    0.46
     `'\\
    0.46
    el
    0.46
     highway
    0.45
    POSITIVE LOGITS
    _),
    0.53
     GetComponent
    0.51
     adob
    0.47
    Cc
    0.47
     ক্যান্টনমেন্ট
    0.47
    OCCO
    0.47
    ক্ষম
    0.46
    AVI
    0.45
    /),
    0.43
    નેસ
    0.42
    Activations Density 0.000%

    No Known Activations