© 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. 74724
    Prev
    Next
    INDEX
    Explanations

    academic, but, a lot

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

    negotiations or specific contexts

    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
    d
    0.58
    чі
    0.49
    don
    0.49
    beauty
    0.48
    dummies
    0.48
    лли
    0.48
    ri
    0.48
    hound
    0.47
    del
    0.47
    f
    0.47
    POSITIVE LOGITS
     akademik
    0.45
    그러나
    0.45
    了很多
    0.45
     Mà
    0.45
     لكن
    0.44
     الكثير
    0.44
     académica
    0.43
     télévision
    0.43
     אבל
    0.42
     obtenu
    0.42
    Activations Density 0.000%

    No Known Activations