© 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. 178928
    Prev
    Next
    INDEX
    Explanations

    make cleanup, voice calls

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

    ghazal, The Descent, expand, tone

    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
    ân
    0.53
    illées
    0.50
    рий
    0.50
    តិ
    0.50
     લે
    0.49
    ْد
    0.49
    锼
    0.48
    чее
    0.47
    દાન
    0.47
    レー
    0.47
    POSITIVE LOGITS
     명이
    0.45
     mellow
    0.43
     del
    0.41
     seer
    0.40
     "
    0.40
    म
    0.40
     Mà
    0.39
    特的
    0.39
     每个
    0.38
    ሚ
    0.38
    Activations Density 0.001%

    No Known Activations