© 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. 250670
    Prev
    Next
    INDEX
    Explanations

    every submarket or antique Europe

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Member
    0.55
    Members
    0.51
    MessageBox
    0.49
    峒
    0.46
    VU
    0.46
    sit
    0.46
    Delivery
    0.46
    MS
    0.46
    DS
    0.45
    Getter
    0.45
    POSITIVE LOGITS
     चढ
    0.50
     कार्यवाही
    0.48
     cons
    0.47
     შეიძ
    0.47
     Zeitschrift
    0.46
     trgov
    0.46
     terminates
    0.45
     Indicates
    0.45
     c
    0.45
     ₽
    0.45
    Activations Density 0.000%

    No Known Activations