© 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. 222669
    Prev
    Next
    INDEX
    Explanations

    specific locations and items

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

    avoiding lard

    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
     কমপক্ষে
    0.52
     ⋮
    0.50
     permissive
    0.49
     เปลี่ยน
    0.48
    ⴹ
    0.48
    >∕</
    0.48
    ometime
    0.47
     Defendant
    0.47
     defendant
    0.47
    हाना
    0.47
    POSITIVE LOGITS
    "
    0.47
    co
    0.45
    ிலிருந்த
    0.42
    dag
    0.41
    (
    0.40
    álló
    0.39
    ar
    0.39
    ri
    0.39
    ref
    0.39
    𝕣
    0.39
    Activations Density 0.000%

    No Known Activations