© 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. 216792
    Prev
    Next
    INDEX
    Explanations

    foreign language tokens

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

    targeting large, convert sunlight, fewer things

    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
    anut
    0.51
    ("\"
    0.48
     }}{
    0.45
     کیس
    0.45
     nutrient
    0.45
     by
    0.45
    thrombin
    0.44
    ва
    0.44
     стати
    0.44
     то
    0.43
    POSITIVE LOGITS
     dritten
    0.59
     manhã
    0.55
     reik
    0.55
    ഒ
    0.52
     vrouw
    0.51
     neue
    0.51
     álgebra
    0.50
    溘
    0.50
     retten
    0.50
    йд
    0.50
    Activations Density 0.001%

    No Known Activations