© 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. 98787
    Prev
    Next
    INDEX
    Explanations

    may apply, variety of

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

    emphasis and conditional scenarios

    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
    usr
    0.53
    .
    0.49
    eding
    0.48
    -
    0.47
    aded
    0.45
    て
    0.44
    aza
    0.44
    ch
    0.43
    fib
    0.43
    た
    0.43
    POSITIVE LOGITS
     Quellen
    0.52
     divertida
    0.51
     wrestlers
    0.51
     করিত
    0.50
    ফটেন্যান্ট
    0.50
     entsprechenden
    0.49
     Schauspieler
    0.48
    ^{*}$
    0.48
     divertido
    0.46
     Ferien
    0.46
    Activations Density 0.003%

    No Known Activations