© 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. 174870
    Prev
    Next
    INDEX
    Explanations

    paralysis

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

    **collection**, acknowledges, pixel, computing

    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
    А
    0.53
    莓
    0.49
    Sunny
    0.48
    ixels
    0.46
    Ｎ
    0.46
    十五
    0.45
     Система
    0.45
    /**
    0.45
     sweetly
    0.45
    asText
    0.45
    POSITIVE LOGITS
     altri
    0.51
     paralyzed
    0.51
     u
    0.49
     course
    0.49
     }_{\
    0.49
     paralysis
    0.47
     Paral
    0.47
     fron
    0.47
     oo
    0.46
     paral
    0.46
    Activations Density 0.001%

    No Known Activations