© 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. 101003
    Prev
    Next
    INDEX
    Explanations

    apparent pterosaurs

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

    approximate averages

    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
     և
    0.46
    และ
    0.44
     आणि
    0.43
    াকর
    0.41
     અને
    0.40
     अक्षर
    0.40
    常に
    0.39
     همیشه
    0.39
    ıp
    0.39
    ⬝
    0.39
    POSITIVE LOGITS
     dumpling
    0.55
     mogelijkheden
    0.50
     오전
    0.50
    見積
    0.49
     dumplings
    0.49
     crepe
    0.49
    午前
    0.49
    ベージュ
    0.49
     低
    0.48
     manhã
    0.48
    Activations Density 0.003%

    No Known Activations