© 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. 16247
    Prev
    Next
    INDEX
    Explanations

    numbers like phone numbers

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

    numbers followed by punctuation

    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
    し
    0.68
    i
    0.68
    个
    0.68
    रा
    0.64
    "))
    0.63
     osobe
    0.59
    つつ
    0.57
     terenie
    0.57
    드
    0.56
    '
    0.55
    POSITIVE LOGITS
    го
    0.83
    arán
    0.83
    can
    0.79
    وين
    0.76
     semblables
    0.76
    ел
    0.76
    нга
    0.75
    ين
    0.74
    ાર
    0.73
    ни
    0.71
    Activations Density 0.036%

    No Known Activations