© 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. 16-GEMMASCOPE-2-RES-16K
    7. 401
    Prev
    Next
    INDEX
    Explanations

    challenge and numbers

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

    have a

    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_16_width_16k_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
     toep
    0.60
     televisi
    0.59
    ский
    0.59
    や
    0.59
    راس
    0.56
    یر
    0.56
    شش
    0.55
     pháp
    0.54
     lintas
    0.52
     määr
    0.52
    POSITIVE LOGITS
     Foreground
    0.48
     Convenience
    0.48
    git
    0.47
    endom
    0.47
    Statement
    0.46
    den
    0.45
    gium
    0.45
    cpu
    0.45
    <<<<
    0.45
     Libertad
    0.45
    Activations Density 0.000%

    No Known Activations