© 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. 57740
    Prev
    Next
    INDEX
    Explanations

    source of within

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

    non-english 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
    ியில்
    0.45
     Stir
    0.45
    㐫
    0.44
    বির
    0.44
    ანი
    0.44
    stir
    0.43
    ியை
    0.42
    itorio
    0.42
    টের
    0.42
    anter
    0.42
    POSITIVE LOGITS
     gelungen
    0.51
     أي
    0.50
     wanneer
    0.48
     ذ
    0.47
     tät
    0.47
     كلمات
    0.46
     mellom
    0.46
     باذن
    0.46
     ob
    0.45
     الأمريكية
    0.45
    Activations Density 0.000%

    No Known Activations