© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213476
    Prev
    Next
    INDEX
    Explanations

    made or forming

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

    ways and policy

    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
    Negative Logits
     Edmonds
    0.48
     <
    0.46
     Euse
    0.45
     (<
    0.44
     충
    0.44
     Verstappen
    0.44
     Е
    0.44
    <0xE2>
    0.43
     с
    0.43
     I
    0.42
    POSITIVE LOGITS
    ggac
    0.50
    رسٹ
    0.50
    ylabel
    0.48
    اضره
    0.47
    GAIN
    0.45
    jLabel
    0.44
     dainty
    0.44
    jsdel
    0.43
     tadi
    0.43
    থন
    0.43
    Activations Density 0.000%

    No Known Activations