© 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. 114401
    Prev
    Next
    INDEX
    Explanations

    preliminary and subject to change

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

    desire, inclination, or subsequent action

    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
    laying
    0.56
     синте
    0.50
     атаку
    0.49
    ₀
    0.46
    launched
    0.45
     codon
    0.45
     ответ
    0.45
     합성
    0.45
     lanzado
    0.44
    onset
    0.44
    POSITIVE LOGITS
     Pittsburg
    0.48
     Russel
    0.46
     Wain
    0.46
     Dik
    0.44
     Margarita
    0.43
     Tatha
    0.43
     गरि
    0.43
    ienz
    0.42
     Á
    0.42
     Marriott
    0.42
    Activations Density 0.002%

    No Known Activations