© 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. 36721
    Prev
    Next
    INDEX
    Explanations

    numbers and sequence

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

    list separators and parenthetical explanations

    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
    .
    0.55
    mi
    0.44
    ans
    0.44
     primal
    0.43
    itet
    0.42
    ae
    0.41
    ia
    0.41
    art
    0.40
    就有
    0.40
     વાત
    0.40
    POSITIVE LOGITS
     худож
    0.50
    린다
    0.50
     vorm
    0.50
    ש
    0.50
    នូវ
    0.48
     відбу
    0.47
     yıllık
    0.47
     органів
    0.47
    Бе
    0.46
    вает
    0.46
    Activations Density 0.000%

    No Known Activations