© 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. 189040
    Prev
    Next
    INDEX
    Explanations

    years ago

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

    spreading elsewhereallows businesseshowever proceed

    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
    Λ
    0.57
    Σ
    0.55
    CS
    0.55
    ฟ
    0.52
    AND
    0.50
    Ř
    0.50
    and
    0.49
    ส
    0.49
    Ä
    0.48
    C
    0.47
    POSITIVE LOGITS
     غرب
    0.51
     тра
    0.50
     ترا
    0.50
     连接
    0.47
     دعم
    0.46
     وخ
    0.46
    addHandler
    0.46
     transformative
    0.44
     مراسم
    0.43
     не
    0.42
    Activations Density 0.001%

    No Known Activations