© 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. 75938
    Prev
    Next
    INDEX
    Explanations

    survival of the fittest

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

    Survival of the fittest

    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
     resonator
    0.49
     Poi
    0.48
    욌
    0.47
     regeneration
    0.45
     secre
    0.44
    豐富
    0.44
     sculpture
    0.44
    親
    0.44
     enquire
    0.44
    аз
    0.43
    POSITIVE LOGITS
     मल्
    0.46
     الأمريكي
    0.46
    狠狠
    0.46
    🌪
    0.44
     مقابلہ
    0.44
     Across
    0.43
    และความ
    0.42
    iejs
    0.42
     پیچھے
    0.41
     బాగా
    0.40
    Activations Density 0.000%

    No Known Activations