© 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. 227688
    Prev
    Next
    INDEX
    Explanations

    years followed by punctuation or sentence break

    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
    ند
    0.55
    న్
    0.54
     ক্লা
    0.47
    掊
    0.47
    ница
    0.47
    آن
    0.46
     विभागीय
    0.45
     فیصلہ
    0.45
    JsonPart
    0.45
    醀
    0.45
    POSITIVE LOGITS
    ot
    0.70
    om
    0.59
    uq
    0.58
    uu
    0.58
    ZZ
    0.58
    i
    0.57
    ox
    0.57
    _
    0.57
    otp
    0.56
    as
    0.54
    Activations Density 0.000%

    No Known Activations