© 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. 69612
    Prev
    Next
    INDEX
    Explanations

    dollar amount followed by number

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

    descriptive words and phrases

    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
     many
    0.65
    many
    0.61
    c
    0.57
     अनुशंसा
    0.52
    Assistant
    0.50
     scholarships
    0.48
    FTP
    0.48
     antire
    0.47
     certifications
    0.47
    Ftp
    0.47
    POSITIVE LOGITS
    єї
    0.65
    طة
    0.53
    міст
    0.49
    шої
    0.48
    মাত্রা
    0.48
    ሒ
    0.47
    䟧
    0.47
    hende
    0.47
    ogenen
    0.46
    ין
    0.46
    Activations Density 0.001%

    No Known Activations