© 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. 77513
    Prev
    Next
    INDEX
    Explanations

    email address for contact

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

    of

    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
     previewBuilder
    0.48
     둘
    0.46
     Fewer
    0.44
     wygl
    0.44
     افغانستان
    0.44
     научных
    0.43
    魟
    0.43
     своему
    0.42
     пове
    0.42
     Meu
    0.42
    POSITIVE LOGITS
    protect
    0.54
    lr
    0.52
    ty
    0.48
    promise
    0.48
    gra
    0.46
    庫
    0.46
    so
    0.46
    ll
    0.46
    st
    0.46
    t
    0.46
    Activations Density 0.001%

    No Known Activations