© 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. 148544
    Prev
    Next
    INDEX
    Explanations

    One Piece, FAIRY TAIL

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

    limited scope or proper function

    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
    θεί
    0.46
    疗
    0.46
    ковое
    0.46
     पाहिजे
    0.43
     lâm
    0.42
    πτυ
    0.41
     사람이
    0.41
     IRB
    0.41
    淫
    0.40
     일이
    0.40
    POSITIVE LOGITS
    )};
    0.47
    entes
    0.46
    ers
    0.44
    '},
    0.44
    ate
    0.44
     Nachrichten
    0.44
     wohl
    0.43
     Italy
    0.43
    0.42
    requenz
    0.42
    Activations Density 0.001%

    No Known Activations