© 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. 198345
    Prev
    Next
    INDEX
    Explanations

    1/ followed by numbers or letters

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

    numbers and descriptive 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
    σου
    0.49
    но
    0.48
    िक
    0.47
    नि
    0.47
    ლო
    0.45
    Discuss
    0.43
    니
    0.43
    Incorpor
    0.42
     sor
    0.42
    िलासपुर
    0.41
    POSITIVE LOGITS
     upto
    0.55
    arms
    0.52
     up
    0.50
     دہشت
    0.47
     లక్ష
    0.46
     +/-
    0.46
    unn
    0.46
     LocalDateTime
    0.46
     growths
    0.45
     lên
    0.45
    Activations Density 0.000%

    No Known Activations