© 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. 243007
    Prev
    Next
    INDEX
    Explanations

    sealed upCandidates mayname hemy favoritecompleted serviceat service

    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
    ກັບ
    0.52
    近年来
    0.52
     앞으로
    0.51
    儿童
    0.50
    ừ
    0.49
    ızlı
    0.48
     Lark
    0.48
    ∀
    0.48
    颁
    0.48
     עם
    0.47
    POSITIVE LOGITS
     Daytona
    0.46
    ayment
    0.44
    at
    0.41
    apy
    0.40
     nachdem
    0.38
    u
    0.38
    デー
    0.38
     Photograph
    0.37
    ทะเบียน
    0.37
     unmittelbar
    0.37
    Activations Density 0.001%

    No Known Activations