© 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. 239763
    Prev
    Next
    INDEX
    Explanations

    e-file IRS Form 1099-R

    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
    ጬ
    0.49
     হাসপাত
    0.46
    بل
    0.46
     tumeurs
    0.45
    ۥ
    0.45
    евна
    0.44
    τερ
    0.44
    тельность
    0.43
    小麦
    0.43
    塹
    0.43
    POSITIVE LOGITS
     Tasty
    0.50
     Tah
    0.45
    kid
    0.44
     TAT
    0.44
    inguistic
    0.44
     Kamis
    0.43
    콰
    0.43
     Super
    0.43
     pod
    0.43
    uvos
    0.43
    Activations Density 0.000%

    No Known Activations