© 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. 17538
    Prev
    Next
    INDEX
    Explanations

    numbers and "of principal"

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

    words in multiple languages

    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
    鸪
    0.42
    橼
    0.40
     ممال
    0.39
    谜
    0.39
    ارد
    0.38
    鸦
    0.38
    εσ
    0.37
    ບັນ
    0.36
    民众
    0.36
    畲
    0.35
    POSITIVE LOGITS
    with
    0.47
    but
    0.45
    and
    0.44
    aj
    0.43
    that
    0.43
    while
    0.42
    fo
    0.41
    ul
    0.41
    which
    0.41
    key
    0.40
    Activations Density 0.017%

    No Known Activations