© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35257
    Prev
    Next
    INDEX
    Explanations

    chocolate MARY

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

    evaluating qualities and trends

    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
    ാം
    0.49
    []}
    0.44
    ೧
    0.44
     Разби
    0.43
     ยก
    0.43
     १०
    0.42
     ១
    0.42
    ༎
    0.42
     бед
    0.41
     घालून
    0.41
    POSITIVE LOGITS
     কিংবা
    0.51
     nativity
    0.45
     või
    0.44
     sash
    0.42
     maintains
    0.42
     furnishing
    0.42
     augmentation
    0.41
    あるいは
    0.41
     upon
    0.41
     nữa
    0.41
    Activations Density 0.000%

    No Known Activations