© 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. 221868
    Prev
    Next
    INDEX
    Explanations

    admits she, insufficient best, ANY telephone, learns that, NOC allows

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

    describing characteristics or comparisons

    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
     ইহ
    0.53
     buildFor
    0.52
     экземпля
    0.51
    𝚋
    0.50
    nements
    0.49
     વ્યક્તિ
    0.48
     miesią
    0.48
    镤
    0.48
     proprietà
    0.48
     व्यक्ति
    0.47
    POSITIVE LOGITS
     grassland
    0.48
     battlefield
    0.46
     flank
    0.45
    p
    0.45
     groaned
    0.44
     ground
    0.44
     sure
    0.42
     grin
    0.42
     planner
    0.42
     task
    0.41
    Activations Density 0.001%

    No Known Activations