© 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. 183727
    Prev
    Next
    INDEX
    Explanations

    exhibits in

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

    describing wrinkles on faces

    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
    티
    0.49
    머
    0.45
    为您
    0.44
    론
    0.43
    风险
    0.43
    트를
    0.42
    테
    0.42
    텍
    0.42
    멜
    0.42
    енти
    0.41
    POSITIVE LOGITS
     জ্ঞ
    0.55
    ou
    0.54
     is
    0.52
    of
    0.52
    orable
    0.52
     itself
    0.52
    at
    0.52
    ample
    0.52
     also
    0.50
     could
    0.50
    Activations Density 0.001%

    No Known Activations