© 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. 160039
    Prev
    Next
    INDEX
    Explanations

    phases of the moon

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

    characters per token

    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
     ܕ
    0.52
    στά
    0.51
     మహా
    0.51
     inhaling
    0.49
     ஃப
    0.47
     hiçbir
    0.46
    .-\
    0.46
     dhamme
    0.46
    ACIÓN
    0.45
     דבר
    0.45
    POSITIVE LOGITS
     american
    0.47
    或
    0.44
     Scotland
    0.42
    toast
    0.41
    や
    0.41
     et
    0.41
    懂
    0.40
    ̫
    0.40
     American
    0.39
     Montag
    0.39
    Activations Density 0.001%

    No Known Activations