© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    while also

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

    while also

    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
    ना
    0.66
     kaleidoscopic
    0.63
     giornata
    0.63
     photometric
    0.61
     nonequilibrium
    0.57
     luscious
    0.57
     مشینوں
    0.57
    ن
    0.57
    ले
    0.56
     comulti
    0.56
    POSITIVE LOGITS
     also
    0.84
    K
    0.74
     også
    0.72
    B
    0.70
     Also
    0.65
    t
    0.64
    Also
    0.63
     також
    0.63
    也是
    0.62
     также
    0.61
    Activations Density 0.063%

    No Known Activations