© 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. 187256
    Prev
    Next
    INDEX
    Explanations

    (by cookie

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

    relationship, employee, speeds, maximize

    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
     بیا
    0.47
     ਸਿੰ
    0.47
    Ph
    0.46
    ph
    0.46
     或
    0.46
    ili
    0.45
     据
    0.45
     प्रदू
    0.45
     polluted
    0.45
     بدا
    0.44
    POSITIVE LOGITS
     armies
    0.51
     Daniels
    0.47
     Garr
    0.46
     lanes
    0.46
     alleys
    0.46
     hardness
    0.46
    谅
    0.46
     Herbert
    0.46
     roughness
    0.45
     decides
    0.44
    Activations Density 0.000%

    No Known Activations