© 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. 189676
    Prev
    Next
    INDEX
    Explanations

    calculation and watch features

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

    writing scripts, Texas held, input flight

    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
    еру
    0.43
    вовано
    0.41
     都
    0.40
     аргу
    0.40
     Danube
    0.40
     Toul
    0.39
     Bellev
    0.39
    прежнему
    0.39
     проблем
    0.39
    巨
    0.38
    POSITIVE LOGITS
     Calculation
    0.56
     Calculations
    0.54
     calculation
    0.51
    Calculation
    0.50
     wiad
    0.50
    calculation
    0.49
    ności
    0.47
    skateboard
    0.47
     গণনা
    0.46
    picable
    0.46
    Activations Density 0.000%

    No Known Activations