© 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. 158620
    Prev
    Next
    INDEX
    Explanations

    coaching, employed, enriched

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

    verb-noun commands, health topics, wrapper methods, native modules, resident eligibility

    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
    markets
    0.54
     変
    0.52
    плат
    0.50
    タウン
    0.49
    meals
    0.48
     इन्वेस्ट
    0.48
     คะ
    0.47
     知
    0.46
    емся
    0.45
    itime
    0.45
    POSITIVE LOGITS
     عندنا
    0.48
     الطب
    0.46
     তখন
    0.45
     tetragonal
    0.44
     wtedy
    0.44
     stutter
    0.43
     garg
    0.43
     режими
    0.43
     fenô
    0.43
    ویی
    0.42
    Activations Density 0.001%

    No Known Activations