© 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. 34730
    Prev
    Next
    INDEX
    Explanations

    All Rights Reserved

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

    All rights reserved

    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
    ন
    0.47
    identified
    0.47
     النبي
    0.46
    ferrer
    0.45
    イッチ
    0.45
    ží
    0.45
    ция
    0.44
    হি
    0.43
     ঘা
    0.43
     Morg
    0.43
    POSITIVE LOGITS
     Globally
    0.43
    👱
    0.40
    𝟬
    0.39
     Vlad
    0.38
     بیا
    0.38
     wrongdoing
    0.38
     deserialize
    0.38
    📲
    0.38
     demonic
    0.37
     disobedience
    0.37
    Activations Density 0.002%

    No Known Activations