© 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. 211820
    Prev
    Next
    INDEX
    Explanations

    insurance services

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

    Skinner jumps, proving accidents

    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
     Siz
    0.52
    du
    0.49
     photographs
    0.48
    ون
    0.47
    l
    0.47
     Suck
    0.47
    IO
    0.46
     Shake
    0.46
    shake
    0.46
     analogies
    0.45
    POSITIVE LOGITS
    䙲
    0.54
     frühen
    0.49
    cenie
    0.49
    ckte
    0.49
     nächste
    0.48
    werte
    0.48
    <
    0.48
    <0x80>
    0.47
     näch
    0.46
     التعامل
    0.45
    Activations Density 0.000%

    No Known Activations