© 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. 87480
    Prev
    Next
    INDEX
    Explanations

    specific continuations

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

    defining or describing lists

    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
     GSi
    0.55
    などが
    0.52
    ﻏ
    0.52
     sím
    0.50
    阌
    0.50
     Administrat
    0.49
    シス
    0.48
     inclusiv
    0.48
    拢
    0.48
    郅
    0.48
    POSITIVE LOGITS
    alupe
    0.51
    us
    0.50
    merk
    0.50
    boosting
    0.49
    vaart
    0.49
    ate
    0.48
    ember
    0.47
    ry
    0.47
    stimulated
    0.46
    watcher
    0.46
    Activations Density 0.001%

    No Known Activations