© 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. 213250
    Prev
    Next
    INDEX
    Explanations

    poker online, faster than

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

    without warning

    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
    e
    0.52
    }
    0.52
    $
    0.51
    i
    0.48
    j
    0.47
    CASE
    0.47
    rijk
    0.47
     Slaughter
    0.46
    Tel
    0.46
     butchers
    0.46
    POSITIVE LOGITS
    áme
    0.55
    荨
    0.55
    యా
    0.50
     resorption
    0.50
     modulation
    0.47
     inflammation
    0.47
     metabolismo
    0.47
    வாக
    0.47
    ॅमिली
    0.46
     pressione
    0.46
    Activations Density 0.000%

    No Known Activations