© 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. 180739
    Prev
    Next
    INDEX
    Explanations

    application, death, flame, covers, pain, blog

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

    explaining details and scenarios

    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
    r
    0.58
    n
    0.57
    s
    0.57
    ng
    0.52
     They
    0.52
     and
    0.50
    est
    0.50
     I
    0.50
    hood
    0.49
    nn
    0.49
    POSITIVE LOGITS
     細胞
    0.57
    hitth
    0.57
    ASCADE
    0.56
     জীবা
    0.56
     शतक
    0.55
     लाभदायक
    0.54
     açúcar
    0.54
     オール
    0.54
    लिये
    0.53
     என்பத
    0.52
    Activations Density 0.001%

    No Known Activations