© 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. 216332
    Prev
    Next
    INDEX
    Explanations

    design concepts

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

    transitioning imagery or information

    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
    原料
    0.50
    bite
    0.48
    ժ
    0.46
    ANGMAR
    0.46
    amasını
    0.45
    전에
    0.45
    NH
    0.45
    ఎస్
    0.45
    <0xC4>
    0.44
     auparavant
    0.44
    POSITIVE LOGITS
     Creat
    0.50
     Metabolism
    0.49
     mirrors
    0.47
     Metabol
    0.46
     Complaints
    0.45
     Bluetooth
    0.43
     Stam
    0.43
    zenie
    0.43
     stre
    0.42
     metabolism
    0.42
    Activations Density 0.000%

    No Known Activations