© 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. 219791
    Prev
    Next
    INDEX
    Explanations

    names or foreign words

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

    helps me understand

    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
     మరియు
    0.51
    厠
    0.48
     ಹಾಗೂ
    0.45
    元の
    0.44
    到達
    0.43
    ين
    0.43
     Tutorial
    0.43
    重複
    0.43
    澤
    0.42
     và
    0.42
    POSITIVE LOGITS
    alan
    0.55
    guan
    0.52
    embl
    0.51
    aków
    0.50
    o
    0.50
    adion
    0.50
    ail
    0.49
    alang
    0.49
    yong
    0.47
    ano
    0.46
    Activations Density 0.003%

    No Known Activations