© 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. 221643
    Prev
    Next
    INDEX
    Explanations

    licensed plugin

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

    essential commands in technical context

    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
    iare
    0.47
    kjav
    0.46
    uega
    0.46
    uig
    0.46
    z
    0.45
    iexpress
    0.45
    cine
    0.45
    iaz
    0.44
    pana
    0.44
    apay
    0.44
    POSITIVE LOGITS
    SScript
    0.48
     But
    0.48
    ても
    0.46
     但
    0.44
     Stück
    0.44
    কিন্তু
    0.44
     McCulloch
    0.44
     ĝi
    0.43
     いっ
    0.43
     ono
    0.43
    Activations Density 0.000%

    No Known Activations