© 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. 202612
    Prev
    Next
    INDEX
    Explanations

    workmanship and quality guarantees

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

    recipes, overwhelmingly built, maintenance

    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
     lakini
    0.50
    ŭ
    0.50
    тик
    0.46
    但是我
    0.45
    uku
    0.45
    z
    0.44
    but
    0.41
    ร
    0.41
    туи
    0.40
     туда
    0.40
    POSITIVE LOGITS
     নিঃসন্দেহে
    0.42
     والدین
    0.41
     يجعل
    0.41
    parentId
    0.38
     Ebert
    0.38
     dólares
    0.38
     honti
    0.38
     achar
    0.38
    ത്തിലുള്ള
    0.38
     conceit
    0.38
    Activations Density 0.000%

    No Known Activations