© 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. 128936
    Prev
    Next
    INDEX
    Explanations

    speech, media, information, conditions

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

    code context with numbers

    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
    稒
    0.54
    するため
    0.52
     arba
    0.51
    ωσε
    0.51
     توانید
    0.49
     പ്രശ്
    0.48
    または
    0.48
    ⿶
    0.48
    Bibitem
    0.48
    বিদ্যা
    0.48
    POSITIVE LOGITS
     sphinct
    0.49
     stunts
    0.49
     použív
    0.49
     greens
    0.48
    -
    0.48
     of
    0.48
     mains
    0.47
    yp
    0.47
     in
    0.46
    ám
    0.45
    Activations Density 0.001%

    No Known Activations