© 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. 121615
    Prev
    Next
    INDEX
    Explanations

    goals and experiences

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

    sequences following certain words

    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
     {
    0.52
     Components
    0.47
     [
    0.46
     §
    0.46
     $
    0.46
     *
    0.46
     !(
    0.45
     "
    0.45
     '+
    0.45
     els
    0.44
    POSITIVE LOGITS
    がる
    0.52
    <unused39>
    0.51
    Interpretation
    0.50
     geologic
    0.47
    발
    0.47
    ête
    0.47
    ście
    0.47
    aży
    0.45
    غیر
    0.45
    üml
    0.45
    Activations Density 0.000%

    No Known Activations