© 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. 232636
    Prev
    Next
    INDEX
    Explanations

    know you

    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
    łej
    0.57
    RICH
    0.56
    Rich
    0.53
    rich
    0.51
    ŝ
    0.51
    사람
    0.49
    Ĥ
    0.49
    uidado
    0.49
    錢
    0.49
     वेळी
    0.48
    POSITIVE LOGITS
     polymorphisms
    0.56
     catheters
    0.56
     allergies
    0.53
     cravings
    0.52
     stressors
    0.52
     enquiries
    0.49
     carcinoma
    0.49
     arthritis
    0.48
     amyloid
    0.48
     impairment
    0.47
    Activations Density 0.001%

    No Known Activations