© 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. 96840
    Prev
    Next
    INDEX
    Explanations

    search engines

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

    flicker, dancing shadows

    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
    rentice
    0.45
    sss
    0.42
     tanggal
    0.40
    k
    0.40
    cse
    0.40
    स्वरूप
    0.39
     Platforms
    0.39
    مرار
    0.38
    ampang
    0.38
    czak
    0.38
    POSITIVE LOGITS
    峄
    0.58
     compétition
    0.52
     countDown
    0.52
    ຂໍ້ມ
    0.51
     высоту
    0.51
    ิน
    0.49
     laissé
    0.49
     ThinQ
    0.49
     ঘটনাস্থ
    0.48
    우
    0.47
    Activations Density 0.000%

    No Known Activations