© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    caveman, just, too, improve, veggies

    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
     なお
    0.50
     Maugin
    0.47
     рэгістра
    0.47
    <unused77>
    0.44
     Idani
    0.44
     imidazole
    0.43
     ईमित्र
    0.43
     gmail
    0.42
     ricevere
    0.42
     honti
    0.42
    POSITIVE LOGITS
    为
    0.45
     two
    0.45
     three
    0.45
     '
    0.44
     a
    0.44
     six
    0.44
    三个
    0.43
     মুক্তিযুদ্ধের
    0.42
    Collapsed
    0.42
     испо
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.