© 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. 226613
    Prev
    Next
    INDEX
    Explanations

    fiscal sponsorship

    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
     repar
    0.51
     bitter
    0.50
     slew
    0.48
    ة
    0.46
    业
    0.46
     bitterly
    0.43
    رحمن
    0.42
    0.42
    柱
    0.42
    ing
    0.41
    POSITIVE LOGITS
     выбрали
    0.53
     மணி
    0.53
     OTHER
    0.52
     приве
    0.51
    textArea
    0.50
     கண்
    0.50
    mique
    0.50
     Illuminated
    0.49
    onChange
    0.49
     ඔවුන්
    0.48
    Activations Density 0.001%

    No Known Activations