© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15460
    Prev
    Next
    INDEX
    Explanations

    numerical approximation methods

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

    numerical computation and methods

    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_16k_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
    en
    0.63
    information
    0.57
    d
    0.56
    elapsed
    0.55
    ulated
    0.54
    defined
    0.54
    enal
    0.52
    al
    0.52
    ol
    0.52
    coords
    0.51
    POSITIVE LOGITS
     Anbieter
    0.49
     utilisons
    0.46
    와의
    0.45
     Ağustos
    0.45
     kuda
    0.45
    ي
    0.45
    燴
    0.44
     maneiras
    0.44
    Autres
    0.43
     ماشي
    0.43
    Activations Density 0.002%

    No Known Activations