© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    because

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

    because

    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
    /
    0.51
     or
    0.50
     of
    0.48
     DeFi
    0.47
     emblematic
    0.47
    0.47
     periods
    0.46
     companions
    0.44
    ↵↵
    0.43
     disguised
    0.43
    POSITIVE LOGITS
     Çünkü
    0.61
     çünkü
    0.59
     γιατί
    0.59
     omdat
    0.59
     gdyż
    0.58
    無視
    0.58
     因為
    0.57
     बिकॉज
    0.57
     لأن
    0.56
     BECAUSE
    0.56
    Activations Density 0.000%

    No Known Activations