© 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. 133779
    Prev
    Next
    INDEX
    Explanations

    guide and discovery

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

    offering information and stating limitations

    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
     machines
    0.50
     localtime
    0.49
     panjang
    0.47
     textColor
    0.47
     tableware
    0.46
     s
    0.46
     phones
    0.45
     Branding
    0.45
     rencana
    0.45
     stadion
    0.45
    POSITIVE LOGITS
    arino
    0.57
    ج
    0.56
    는
    0.55
    א
    0.54
    ar
    0.54
    אה
    0.54
    ها
    0.53
    은
    0.51
    ඖ
    0.51
    sett
    0.50
    Activations Density 0.001%

    No Known Activations