© 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. 150978
    Prev
    Next
    INDEX
    Explanations

    mission trips

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

    evokes imagery, prayers

    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
     పూర్తిగా
    0.50
    ంగళ
    0.42
    皤
    0.42
     मुताब
    0.40
     %><%=
    0.40
     लाहिड़ी
    0.40
    exporter
    0.40
     जाएंगी
    0.40
     overarching
    0.40
     excellently
    0.40
    POSITIVE LOGITS
     collectif
    0.48
     aquí
    0.48
    ِی
    0.48
     lesión
    0.47
     sini
    0.46
     venit
    0.46
    。
    0.46
     לי
    0.45
     ayrıca
    0.45
     soğ
    0.44
    Activations Density 0.000%

    No Known Activations