© 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. 158286
    Prev
    Next
    INDEX
    Explanations

    longest serving

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

    describing programming functions

    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
     Kirst
    0.42
     dabb
    0.42
    ofacial
    0.42
    ixel
    0.39
     tatsächlich
    0.39
    面临
    0.39
    adays
    0.39
    !}
    0.38
     capitalismo
    0.38
     fracking
    0.38
    POSITIVE LOGITS
     नतीजा
    0.49
     resultar
    0.47
     सेवन
    0.46
    ्वे
    0.45
    伍章
    0.44
    ूल
    0.44
    करार
    0.44
    typed
    0.43
    न्नी
    0.43
    assurer
    0.43
    Activations Density 0.002%

    No Known Activations