© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47198
    Prev
    Next
    INDEX
    Explanations

    reported, discovered, examine, dietary

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

    physical things or attributes

    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
     utilised
    0.44
    杞
    0.43
     normal
    0.43
     caffeine
    0.42
     benign
    0.42
     remedy
    0.40
     medic
    0.39
     cancerous
    0.39
     cleanly
    0.39
    治疗
    0.38
    POSITIVE LOGITS
     κάτι
    0.56
    !',
    0.52
     ऐतिहासिक
    0.52
     ต
    0.51
    เขา
    0.51
     σημα
    0.50
    !",
    0.50
     कविता
    0.50
    ,_-
    0.50
     بسیار
    0.49
    Activations Density 0.000%

    No Known Activations