© 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. 56190
    Prev
    Next
    INDEX
    Explanations

    part of phrase

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

    code and math concepts

    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
     {
    0.53
    0.50
    sg
    0.46
     poorly
    0.45
     była
    0.44
    Cw
    0.44
    団
    0.44
     a
    0.43
     i
    0.43
     living
    0.43
    POSITIVE LOGITS
     hadrons
    0.54
    صیٰ
    0.52
    uttab
    0.49
    갖
    0.48
     ecuaciones
    0.47
     lineales
    0.47
    ihydro
    0.47
    iazep
    0.46
    لح
    0.46
    SERVIDOR
    0.46
    Activations Density 0.000%

    No Known Activations