© 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. 117562
    Prev
    Next
    INDEX
    Explanations

    customer reviews

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

    how it works

    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
    0.61
     j
    0.54
    _
    0.54
    =
    0.52
     \"
    0.52
    -
    0.50
     _
    0.47
     d
    0.46
    ak
    0.46
    2
    0.46
    POSITIVE LOGITS
     épaisse
    0.55
     obeying
    0.54
     respetar
    0.52
    عنی
    0.52
    ၷ
    0.52
     देवताओं
    0.51
    ッ
    0.51
     سرزمین
    0.51
     encuentren
    0.50
     семейства
    0.50
    Activations Density 0.000%

    No Known Activations