© 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. 60984
    Prev
    Next
    INDEX
    Explanations

    a, A, MSA followed by words

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

    a followed by numbers

    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
    l
    1.02
    k
    1.00
    t
    0.98
    los
    0.93
    st
    0.90
    is
    0.88
    ran
    0.84
    r
    0.83
    lar
    0.82
    lle
    0.82
    POSITIVE LOGITS
    는
    0.82
    ード
    0.79
    ה
    0.75
    اا
    0.72
    ಿಗಳು
    0.70
    くちゃ
    0.68
    ংশের
    0.67
    뵌
    0.66
    foils
    0.66
    ﻓ
    0.66
    Activations Density 0.130%

    No Known Activations