© 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. 39071
    Prev
    Next
    INDEX
    Explanations

    religious figures and texts

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

    lists and numbers

    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
    㴬
    0.17
    肄
    0.15
    Hispanic
    0.15
     agacch
    0.15
    ეგის
    0.14
    Best
    0.14
     vacanam
    0.13
    best
    0.13
     puriso
    0.13
     اعز
    0.13
    POSITIVE LOGITS
     якобы
    0.16
    èdent
    0.15
    ={
    0.15
    lé
    0.15
     روز
    0.14
     ২০২০
    0.14
    冻
    0.14
     olan
    0.14
    0.14
    ਵ
    0.14
    Activations Density 0.000%

    No Known Activations