© 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. 192026
    Prev
    Next
    INDEX
    Explanations

    analysis of CM/CMS

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

    simple, chorus, desires

    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
    ডিয়া
    0.50
     পাশ্চাত্য
    0.50
     ს
    0.48
    កំព
    0.48
    សម
    0.47
    lení
    0.46
    ,-\
    0.46
     પસ
    0.46
     काली
    0.45
    ริกา
    0.43
    POSITIVE LOGITS
    잡
    0.45
    اح
    0.44
     zunächst
    0.44
     armies
    0.44
    6
    0.44
     armed
    0.44
     robbing
    0.43
    grab
    0.43
     devastated
    0.43
    حال
    0.43
    Activations Density 0.000%

    No Known Activations