© 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. 170609
    Prev
    Next
    INDEX
    Explanations

    time updates or finality

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

    gaming streams

    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
     olives
    0.59
     govori
    0.54
     on
    0.53
     sistemat
    0.52
     gore
    0.50
     afric
    0.50
    aya
    0.48
    a
    0.48
     cio
    0.47
     andrew
    0.47
    POSITIVE LOGITS
    晞
    0.56
    寤
    0.49
    炤
    0.48
     کھیلیں
    0.48
    Highly
    0.46
    Lead
    0.45
    无需
    0.45
    泄
    0.45
    шлай
    0.44
    RESS
    0.44
    Activations Density 0.000%

    No Known Activations