© 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. 47441
    Prev
    Next
    INDEX
    Explanations

    any or some

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

    alternatives or choices

    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
    及
    0.49
    不一样
    0.44
    Є
    0.43
    owią
    0.42
    ｊ
    0.42
    queta
    0.41
    移动
    0.41
    및
    0.41
    ϳ
    0.41
    θα
    0.40
    POSITIVE LOGITS
     irgende
    0.59
     irgend
    0.51
     alguno
    0.51
     arba
    0.51
     alguna
    0.47
     alebo
    0.46
     alguma
    0.46
     renversement
    0.45
     няко
    0.44
     hätte
    0.43
    Activations Density 0.001%

    No Known Activations