© 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. 131551
    Prev
    Next
    INDEX
    Explanations

    time units ago

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

    time ago

    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
    ♋
    0.45
     recherche
    0.41
    推荐
    0.40
    prehensive
    0.39
    යක්
    0.38
    မျက်
    0.38
    wają
    0.37
     khuyến
    0.37
    蜢
    0.37
    ifiable
    0.37
    POSITIVE LOGITS
     freeing
    0.44
     agitation
    0.43
    decre
    0.43
    gebra
    0.41
    eks
    0.41
     papers
    0.41
     fortnight
    0.40
     frees
    0.40
     Tf
    0.40
     ago
    0.40
    Activations Density 0.004%

    No Known Activations