© 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. 151630
    Prev
    Next
    INDEX
    Explanations

    weeks per year

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

    date dxdiag modify

    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
    続き
    0.51
    ガ
    0.50
    繋がり
    0.50
    ק
    0.48
    ২
    0.48
    ್ರಾ
    0.45
    ิล
    0.45
    겠지만
    0.45
    সরকারী
    0.45
     Брита
    0.45
    POSITIVE LOGITS
     Without
    0.46
     पीड़ा
    0.42
    allelujah
    0.41
    的一种
    0.41
     环境
    0.41
     mantra
    0.41
     Faster
    0.40
     faster
    0.40
     HOUR
    0.39
    疠
    0.39
    Activations Density 0.002%

    No Known Activations