© 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. 68666
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    production

    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
     =\
    0.44
     королев
    0.43
     probabilities
    0.42
     ariel
    0.42
    発見
    0.42
     parámetros
    0.41
     `{
    0.41
     šk
    0.41
     nonzero
    0.41
     mismos
    0.41
    POSITIVE LOGITS
    currentSprite
    0.52
     Enquanto
    0.48
     sottoline
    0.46
    য়াছে
    0.46
    indre
    0.45
     Burada
    0.45
    esine
    0.45
    ä
    0.45
    ilic
    0.44
     Тогда
    0.44
    Activations Density 0.001%

    No Known Activations