© 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. 198409
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

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

    power of, dream recall, initially, Birds

    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
    馁
    0.49
    ไม้
    0.48
    หัส
    0.47
    \\
    0.45
    tooth
    0.44
    чным
    0.43
    ivasena
    0.43
    ꒷
    0.43
    льным
    0.42
    ammable
    0.42
    POSITIVE LOGITS
     €,
    0.46
    時候
    0.45
     κ
    0.45
     arcu
    0.44
    國民
    0.44
     quadrants
    0.44
     rhiz
    0.43
     Kü
    0.43
     ct
    0.43
    歐洲
    0.43
    Activations Density 0.000%

    No Known Activations