© 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. 167829
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    punctuation around code/data descriptions

    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
     speeds
    0.51
     buds
    0.48
     photons
    0.48
    कित
    0.48
     pups
    0.47
     signals
    0.46
     envelopes
    0.46
    kitt
    0.46
     resellers
    0.45
    릇
    0.45
    POSITIVE LOGITS
    
    0.53
    IBM
    0.47
     很
    0.45
    XMLSchema
    0.45
     副
    0.45
     ["
    0.45
     極
    0.44
     théâtre
    0.44
    ifilm
    0.43
     જેને
    0.43
    Activations Density 0.000%

    No Known Activations