© 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. 9821
    Prev
    Next
    INDEX
    Explanations

    dates and ordinals

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

    numbers, dates, and times

    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
    胙
    0.21
    ပဲ
    0.20
    <unused2107>
    0.20
    <unused1012>
    0.20
    <unused2148>
    0.19
     saddhim
    0.19
     അല്ലെങ്കിൽ
    0.19
    <unused1770>
    0.19
     ویت
    0.19
    <unused309>
    0.19
    POSITIVE LOGITS
    _
    0.40
    -
    0.34
    6
    0.32
    7
    0.31
    8
    0.31
    5
    0.30
    9
    0.30
    4
    0.28
    3
    0.26
    ７
    0.24
    Activations Density 0.286%

    No Known Activations