© 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. 201594
    Prev
    Next
    INDEX
    Explanations

    during or monthly Session

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

    greetings and cost

    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
    ;
    0.54
     nytt
    0.51
     [
    0.50
    [
    0.47
    는
    0.47
    ([
    0.46
     For
    0.45
    ]
    0.45
     F
    0.43
     Am
    0.43
    POSITIVE LOGITS
     andDevice
    0.54
    ÈME
    0.53
     எண்ணெய்
    0.53
    <unused394>
    0.52
    érature
    0.50
    ₂,
    0.49
     சந்திர
    0.49
     нефте
    0.49
    lara
    0.48
    籶
    0.48
    Activations Density 0.001%

    No Known Activations