© 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. 122388
    Prev
    Next
    INDEX
    Explanations

    a single person or entity

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

    specific details and types

    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
    ﻱ
    0.53
    ش
    0.51
    ю
    0.50
    مي
    0.50
    ही
    0.48
    اي
    0.47
    لي
    0.46
     lilac
    0.46
    ट
    0.46
     locale
    0.45
    POSITIVE LOGITS
     लक
    0.46
    的外
    0.46
     앞으로
    0.46
     मुकद
    0.45
     ਜਾ
    0.45
    clerosis
    0.44
     နောက်
    0.44
     除了
    0.44
    ക്കുറ
    0.44
     무엇
    0.43
    Activations Density 0.001%

    No Known Activations