© 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. 110686
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    Proviene de

    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
    ראה
    0.51
     malade
    0.50
    ρώ
    0.50
    ⠉
    0.50
    type
    0.50
    mixing
    0.49
    J
    0.49
    tipo
    0.48
    museum
    0.48
    قافة
    0.47
    POSITIVE LOGITS
    আন্তর্জাতিক
    0.49
     INS
    0.48
    ติ
    0.46
     BEC
    0.45
     ху
    0.45
     ANS
    0.44
     케
    0.44
     सर्वाधिक
    0.44
    angs
    0.42
     ਕੋ
    0.42
    Activations Density 0.000%

    No Known Activations