© 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. 107781
    Prev
    Next
    INDEX
    Explanations

    celebrating home, hesitant sellers, Avengers

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

    file names and data processing

    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
    嚩
    0.41
    انيا
    0.41
    ਆ
    0.40
     للا
    0.40
    溢
    0.40
     لل
    0.39
    িলি
    0.39
    …。
    0.39
    浗
    0.39
    王者
    0.39
    POSITIVE LOGITS
     Kamane
    0.54
    ound
    0.51
    uvieron
    0.49
    Ế
    0.47
    fqsen
    0.46
    hamdul
    0.46
    $\
    0.46
    ரிடம்
    0.46
     Voraussetzungen
    0.46
     texId
    0.45
    Activations Density 0.000%

    No Known Activations