© 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. 77433
    Prev
    Next
    INDEX
    Explanations

    concepts, times, figures

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

    barcodes and scientific terms

    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
    i
    0.52
    St
    0.51
     Commander
    0.49
     동시에
    0.46
    utt
    0.45
    了一个
    0.45
    Commander
    0.44
     Radial
    0.44
     Cadet
    0.43
    此时
    0.42
    POSITIVE LOGITS
    ணத்திற்கு
    0.52
    asati
    0.52
    மாகக்
    0.49
    тан
    0.48
     К
    0.47
     rocked
    0.46
    ாளர்க
    0.46
    kuat
    0.46
     obligated
    0.46
    leşik
    0.45
    Activations Density 0.000%

    No Known Activations