© 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. 69364
    Prev
    Next
    INDEX
    Explanations

    What happens when

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

    conditions or consequences

    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
    Learn
    0.49
    գ
    0.43
    TimeSeries
    0.43
     स्टा
    0.42
    Lessons
    0.41
    יין
    0.41
    Lesson
    0.41
    所在的
    0.41
    引き続き
    0.41
    igkeiten
    0.40
    POSITIVE LOGITS
     bitmaps
    0.48
     Outer
    0.48
     iemand
    0.46
     nests
    0.46
     terá
    0.46
     ⚫
    0.46
     bateria
    0.46
     nebude
    0.46
     الجم
    0.45
    Outer
    0.45
    Activations Density 0.006%

    No Known Activations