© 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. 129504
    Prev
    Next
    INDEX
    Explanations

    for specific contexts

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

    Furthermore, health, timeframe

    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
    Not in Any Lists

    No Comments

    Negative Logits
     reformer
    0.50
     offsetX
    0.46
     decompression
    0.46
     گھ
    0.45
     arcade
    0.45
     Datenbank
    0.44
    鲞
    0.43
     freien
    0.43
     informée
    0.43
     டிக
    0.43
    POSITIVE LOGITS
    f
    0.56
    fors
    0.52
    ajas
    0.51
    ayas
    0.48
    few
    0.47
    ]
    0.47
    k
    0.47
    PM
    0.47
    itiv
    0.47
    ajib
    0.47
    Activations Density 0.000%

    No Known Activations