© 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. 240956
    Prev
    Next
    INDEX
    Explanations

    events or states

    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
     cần
    0.44
    ၏
    0.44
     gaussian
    0.42
     Guangdong
    0.42
     rhod
    0.41
    )
    0.41
     hypotheses
    0.41
     Andersson
    0.40
     새
    0.39
     tốt
    0.39
    POSITIVE LOGITS
    decine
    0.49
    谆
    0.47
    サーバ
    0.45
    囯
    0.45
    sama
    0.44
    之类的
    0.43
    "=>$
    0.42
    Saf
    0.42
    avascript
    0.42
     aprovech
    0.42
    Activations Density 0.001%

    No Known Activations