© 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. 198381
    Prev
    Next
    INDEX
    Explanations

    describing physical size

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

    beauty on, servers to

    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
    ählt
    0.51
    yal
    0.50
    krét
    0.50
    铱
    0.50
     јуну
    0.49
     rupani
    0.48
     रहमान
    0.48
    FlashValue
    0.48
    nią
    0.47
     дослі
    0.47
    POSITIVE LOGITS
     www
    0.50
    θα
    0.50
     WILL
    0.49
     and
    0.49
     transitional
    0.48
    1
    0.46
     θα
    0.46
     http
    0.45
     in
    0.45
     Euler
    0.45
    Activations Density 0.000%

    No Known Activations