© 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. 32662
    Prev
    Next
    INDEX
    Explanations

    mentioned also

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

    continuations and additions

    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
     almighty
    0.58
     sommes
    0.54
     douze
    0.51
     hostility
    0.49
    Ყ
    0.49
     êtres
    0.48
    அல்ல
    0.48
     soyez
    0.48
     murderous
    0.48
    Ნ
    0.47
    POSITIVE LOGITS
     also
    0.66
     επίσης
    0.59
     también
    0.55
     també
    0.55
     again
    0.54
     ankaŭ
    0.54
     également
    0.53
     then
    0.52
     these
    0.52
     Again
    0.51
    Activations Density 0.435%

    No Known Activations