© 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. 94441
    Prev
    Next
    INDEX
    Explanations

    life expectancy, heaven of, she started, drawer credenzas

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

    design and implement

    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
     are
    0.48
     waist
    0.44
     of
    0.43
     breach
    0.43
     diameters
    0.43
     during
    0.43
    amine
    0.42
    ឫ
    0.41
    rying
    0.41
    jede
    0.41
    POSITIVE LOGITS
     tessel
    0.47
    ಗಾರ
    0.47
    ಸ್ಸ
    0.47
    дут
    0.46
    च्छ
    0.46
    的三
    0.46
    یک
    0.46
    行く
    0.45
    Roberto
    0.45
     Three
    0.44
    Activations Density 0.000%

    No Known Activations