© 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-16K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    numbers and awards

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

    percentage numbers and units

    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_16k_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
    ור
    0.49
    ró
    0.49
    ט
    0.48
    ൊ
    0.46
    rane
    0.45
    kern
    0.45
    oddsidemargin
    0.44
    ್ಯ
    0.43
    រ
    0.42
    ры
    0.41
    POSITIVE LOGITS
     __
    0.59
    is
    0.59
     _
    0.53
     contra
    0.52
     galvan
    0.52
    σε
    0.51
     ___
    0.50
     impi
    0.49
     jau
    0.49
     fission
    0.49
    Activations Density 0.263%

    No Known Activations