© 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. 42143
    Prev
    Next
    INDEX
    Explanations

    means that

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

    means

    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
    p
    0.90
    a
    0.79
    c
    0.72
    ד
    0.71
     a
    0.69
    in
    0.66
    st
    0.66
    i
    0.65
     it
    0.64
    it
    0.64
    POSITIVE LOGITS
     että
    0.63
     bahwa
    0.62
     kutoka
    0.61
    濩
    0.59
     bahawa
    0.57
     hogy
    0.54
    酘
    0.54
     تحصیل
    0.53
    拉克
    0.52
     jotka
    0.52
    Activations Density 0.025%

    No Known Activations