© 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. 166383
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

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

    academic papers and institutions

    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
    とその
    0.52
    вето
    0.46
    thebetterindia
    0.45
    ｄ
    0.45
    ポリ
    0.44
    笘
    0.44
    vertx
    0.43
    η
    0.43
    rivia
    0.43
    ｂ
    0.43
    POSITIVE LOGITS
    arz
    0.46
    Trails
    0.40
    ungen
    0.39
     explains
    0.38
     stellen
    0.38
    ផ្តល់
    0.37
    ዣ
    0.37
     tries
    0.37
     చెప్ప
    0.37
    PRODUCTS
    0.37
    Activations Density 0.000%

    No Known Activations