© 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. 94215
    Prev
    Next
    INDEX
    Explanations

    navy blue bathroom accessories

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

    explaining technical concepts and code

    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
    .
    0.47
     Eligibility
    0.47
     road
    0.45
     revolutionary
    0.44
     stethoscope
    0.44
     UNITED
    0.44
     clicks
    0.43
     eligibility
    0.43
     facility
    0.43
     pliers
    0.43
    POSITIVE LOGITS
     destaca
    0.49
    酽
    0.47
     заповед
    0.44
     си
    0.43
     функция
    0.42
     центра
    0.42
     जिज्ञासा
    0.42
     departamento
    0.42
     esencial
    0.41
     সম্পাদ
    0.41
    Activations Density 0.005%

    No Known Activations