© 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. 84835
    Prev
    Next
    INDEX
    Explanations

    straightforward letter

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

    return or again

    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
     Attributes
    0.50
    ﾗ
    0.45
    享有
    0.44
     relativa
    0.43
    完整
    0.43
    ĩnh
    0.43
    geschoss
    0.42
    رحب
    0.42
    ၻ
    0.42
     विविध
    0.42
    POSITIVE LOGITS
     теста
    0.48
     tilbage
    0.47
     دوبارہ
    0.47
    embalikan
    0.47
     доста
    0.45
     Kembali
    0.45
     다시
    0.45
     pagal
    0.44
    教えて
    0.44
    지로
    0.44
    Activations Density 0.000%

    No Known Activations