© 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. 54857
    Prev
    Next
    INDEX
    Explanations

    research group

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

    I would argue for

    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
     prosecutions
    0.47
    hauer
    0.46
     endeavors
    0.46
    鏤
    0.45
     životu
    0.45
     reorgan
    0.44
    حث
    0.44
     emancip
    0.44
     remarkably
    0.43
     belongings
    0.43
    POSITIVE LOGITS
     म्हणतात
    0.51
     Minggu
    0.51
    dois
    0.50
     می‌دهد
    0.49
     Center
    0.49
     শুক্রবার
    0.48
    २
    0.48
     Selon
    0.48
    💑
    0.48
     deux
    0.47
    Activations Density 0.000%

    No Known Activations