© 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. 239876
    Prev
    Next
    INDEX
    Explanations

    Institutions and academic fields

    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
     drab
    0.44
     Anthrop
    0.42
    ȟ
    0.42
    ocultural
    0.41
    aros
    0.41
    nCurr
    0.41
     imassa
    0.39
    둴
    0.39
     specializing
    0.39
     قالت
    0.39
    POSITIVE LOGITS
     ‬
    0.44
    শ্য
    0.41
    )+
    0.41
    大規模
    0.40
    肉
    0.40
     цена
    0.40
    JY
    0.40
    )=
    0.40
    IGH
    0.39
     》
    0.39
    Activations Density 0.002%

    No Known Activations