© 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. 192625
    Prev
    Next
    INDEX
    Explanations

    insurance, hyperlinks, specific words

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

    acquires companies, creating data

    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
    釟
    0.50
    Wij
    0.49
    㝡
    0.49
     trùng
    0.48
    த்தின
    0.47
    quête
    0.47
     सत्ता
    0.47
    SIL
    0.46
    ера
    0.45
    erende
    0.45
    POSITIVE LOGITS
     odnosno
    0.56
     apricot
    0.55
     говорил
    0.53
     Y
    0.52
     gato
    0.49
     y
    0.49
     r
    0.49
     apricots
    0.48
     отделения
    0.48
     psik
    0.47
    Activations Density 0.000%

    No Known Activations