© 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. 186720
    Prev
    Next
    INDEX
    Explanations

    years and numbers

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

    in X words

    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
    l
    0.44
     пять
    0.43
     sensibles
    0.42
     cinq
    0.41
     четы
    0.41
    five
    0.41
    ４
    0.41
     jeudi
    0.41
    blox
    0.41
    lusconi
    0.41
    POSITIVE LOGITS
     Juliana
    0.42
    டித்து
    0.40
     hoogte
    0.40
    ād
    0.40
    病人
    0.39
     கொள்
    0.39
    elaar
    0.39
     Höhe
    0.38
     জুল
    0.38
    镰
    0.38
    Activations Density 0.001%

    No Known Activations