© 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. 219935
    Prev
    Next
    INDEX
    Explanations

    protecting personal information or data

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

    diverse names and languages

    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
    BE
    0.49
     be
    0.48
     originally
    0.48
     omega
    0.48
    𝚋
    0.47
     babe
    0.47
    ب
    0.47
    M
    0.46
     ultram
    0.43
    ↵↵↵↵↵
    0.42
    POSITIVE LOGITS
     টিক্কা
    0.50
     মধ্যেও
    0.48
    чної
    0.47
     اقدامات
    0.47
     Tarifi
    0.46
     Aktion
    0.46
     చర్య
    0.45
    嫐
    0.44
     också
    0.43
    гән
    0.43
    Activations Density 0.000%

    No Known Activations