© 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. 67929
    Prev
    Next
    INDEX
    Explanations

    parts of a system

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

    prioritizing over exhaustive

    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
    ர்
    0.61
    ה
    0.59
    ي
    0.55
    peres
    0.53
     внутри
    0.53
     angered
    0.52
    ।
    0.52
    ިއ
    0.50
     adentro
    0.49
     insides
    0.49
    POSITIVE LOGITS
     Geographic
    0.43
     nominating
    0.41
     Firstly
    0.41
     Investing
    0.41
     Observing
    0.40
     ১৯৭১
    0.39
     Replication
    0.39
     Cause
    0.39
    amic
    0.38
     profe
    0.38
    Activations Density 0.002%

    No Known Activations