© 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. 9944
    Prev
    Next
    INDEX
    Explanations

    index position tracking

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

    loop indices and start points

    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
    üst
    0.50
     zrobić
    0.49
    írus
    0.49
     brû
    0.48
    ukuoka
    0.47
     włas
    0.46
     zamów
    0.46
    嬅
    0.46
    สาว
    0.46
     ゼ
    0.46
    POSITIVE LOGITS
     begin
    0.51
     start
    0.46
    start
    0.45
    startIndex
    0.45
     proceeding
    0.43
    Start
    0.43
     n
    0.43
    下标
    0.42
    START
    0.42
    >
    0.42
    Activations Density 0.000%

    No Known Activations