© 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. 224374
    Prev
    Next
    INDEX
    Explanations

    Ensure survival, stuck, ONLY

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

    what I can do

    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
    مان
    0.52
    ષા
    0.47
    它们的
    0.44
    ول
    0.44
    డో
    0.44
    اني
    0.43
    꿰
    0.42
    رشف
    0.42
    ംഗ്
    0.42
    ULS
    0.42
    POSITIVE LOGITS
    isub
    0.46
    amic
    0.45
    {
    0.45
    _
    0.44
    cone
    0.43
    yste
    0.42
    [
    0.42
    ijing
    0.42
     erhe
    0.41
    iguë
    0.41
    Activations Density 0.000%

    No Known Activations