© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9264
    Prev
    Next
    INDEX
    Explanations

    coffee grounds or Python

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     temperature
    0.55
     manufacturer
    0.52
     denounce
    0.52
     sixth
    0.49
    {
    0.49
    此
    0.49
     höch
    0.47
     unthinkable
    0.47
     playground
    0.46
     revise
    0.45
    POSITIVE LOGITS
    ĝ
    0.49
    gaan
    0.48
    Ridge
    0.47
    jaan
    0.47
    Norton
    0.45
    Rig
    0.45
    Psal
    0.44
    ubwa
    0.43
    Mu
    0.43
     때문에
    0.43
    Activations Density 0.004%

    No Known Activations