© 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. 202668
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions

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

    greater than, slightly less, precision 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
     ако
    0.47
    КА
    0.46
     ساعت
    0.46
     ти
    0.46
     работ
    0.46
     условия
    0.46
     эсте
    0.46
    я
    0.46
    కా
    0.45
     టై
    0.45
    POSITIVE LOGITS
    brug
    0.54
     platform
    0.51
     solenoid
    0.50
     wording
    0.48
     demonic
    0.48
     でも
    0.48
     WPF
    0.46
     Angew
    0.46
     możemy
    0.46
     submodule
    0.46
    Activations Density 0.000%

    No Known Activations