© 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. 9257
    Prev
    Next
    INDEX
    Explanations

    order argument in notify

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

    method parameters and types

    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
    櫂
    0.42
     शू
    0.39
    щин
    0.39
     nominally
    0.38
    োক
    0.36
    ißler
    0.36
     सॉल्यूशन
    0.36
     desperately
    0.36
     integrand
    0.36
     suitably
    0.35
    POSITIVE LOGITS
     _:
    0.39
    context
    0.35
    urb
    0.35
    notice
    0.34
     EventArgs
    0.34
    Genesis
    0.33
    ArrayIndex
    0.33
    Concrete
    0.32
     έγινε
    0.32
     Sime
    0.32
    Activations Density 0.000%

    No Known Activations