© 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. 145726
    Prev
    Next
    INDEX
    Explanations

    intermittent settings and time durations

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

    accurate, quick, skilled

    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
    *.
    0.50
     Ordered
    0.45
     less
    0.44
    *
    0.44
    .*
    0.44
     This
    0.43
    for
    0.43
     for
    0.43
     Seek
    0.43
     |
    0.42
    POSITIVE LOGITS
    픔
    0.51
    മ്പർ
    0.47
    otoxicity
    0.46
    मृत
    0.45
     heartache
    0.45
    คืน
    0.44
     homelessness
    0.44
    ()<<"
    0.44
    humidité
    0.43
     calamities
    0.43
    Activations Density 0.001%

    No Known Activations