© 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. 18923
    Prev
    Next
    INDEX
    Explanations

    list itemization or code structure

    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
     எடுத்துக்கா
    0.43
    бли
    0.43
     सिंपल
    0.42
    о
    0.41
     Captured
    0.40
    蔣
    0.40
    িয়ে
    0.40
    allclasses
    0.39
     unsuspecting
    0.39
    どころ
    0.39
    POSITIVE LOGITS
     توان
    0.55
    trailer
    0.42
     Ω
    0.42
     hadron
    0.40
     trailer
    0.40
     regenerative
    0.40
     mutagenesis
    0.40
     ino
    0.40
     CQG
    0.40
     regen
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.