© 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. 121157
    Prev
    Next
    INDEX
    Explanations

    availability and offers

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

    Algorithms automatically

    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
    օ
    0.49
    у
    0.48
    러스
    0.48
     границы
    0.47
     ESS
    0.45
    ו
    0.44
    પ
    0.43
    ूज
    0.43
     সন্ধান
    0.43
    қ
    0.43
    POSITIVE LOGITS
     beinh
    0.56
     Kapitel
    0.50
     Eind
    0.50
    નને
    0.48
     dinyatakan
    0.48
     Oyster
    0.46
     Yaad
    0.46
     aument
    0.46
     Announced
    0.45
     Paral
    0.44
    Activations Density 0.000%

    No Known Activations