© 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. 185130
    Prev
    Next
    INDEX
    Explanations

    Mass at 11am

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

    Rayleigh scattering

    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
    创作
    0.51
    忏
    0.50
    いただきます
    0.49
    وینت
    0.49
     peneliti
    0.48
    ेच्छा
    0.48
     poetic
    0.48
    学术
    0.48
    嚏
    0.47
     ऑर्ग
    0.46
    POSITIVE LOGITS
    '
    0.46
     )
    0.43
    (=
    0.43
     neglig
    0.42
     ô
    0.42
     frightened
    0.42
     x
    0.42
     ");
    0.42
     ";
    0.41
     tls
    0.41
    Activations Density 0.000%

    No Known Activations