© 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. 137295
    Prev
    Next
    INDEX
    Explanations

    credit options and measurements

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

    complex states and concepts

    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
     immature
    0.48
    坏
    0.47
    버
    0.42
     ਬ
    0.42
    unlist
    0.42
     tumour
    0.41
    這樣子
    0.41
     banked
    0.41
    attacks
    0.40
     rendering
    0.40
    POSITIVE LOGITS
     of
    0.51
     Royaume
    0.50
    サプライ
    0.48
    름
    0.47
     Fac
    0.46
     parla
    0.46
     conforman
    0.46
     acorde
    0.45
    of
    0.45
     Ester
    0.45
    Activations Density 0.003%

    No Known Activations