© 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. 216113
    Prev
    Next
    INDEX
    Explanations

    follow-up information

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

    conditional qualifiers and descriptors

    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
     currant
    0.47
     Accum
    0.46
     multin
    0.46
     misa
    0.46
     رئیس
    0.45
    ワ
    0.45
     latch
    0.44
     Organ
    0.44
     chieftain
    0.44
    ის
    0.44
    POSITIVE LOGITS
    iques
    0.54
    irnya
    0.49
     даже
    0.47
     막
    0.47
     방식으로
    0.47
     حتى
    0.46
     которых
    0.46
    сову
    0.46
     найбільш
    0.46
     подска
    0.45
    Activations Density 0.000%

    No Known Activations