© 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. 29754
    Prev
    Next
    INDEX
    Explanations

    prepositions and specific nouns

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

    completers, equations, color, SNMP

    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
    瘋
    0.48
    マ
    0.45
    อยาก
    0.44
    🌪
    0.43
    ಲ
    0.43
    疯狂
    0.42
    इंडिया
    0.42
    マリ
    0.41
    ว
    0.41
    פ
    0.41
    POSITIVE LOGITS
     جهاز
    0.49
    လည်း
    0.48
     Medications
    0.48
     habían
    0.46
     उपकरणों
    0.46
     যন্ত্র
    0.45
     кое
    0.45
     également
    0.45
     heretofore
    0.44
     někter
    0.43
    Activations Density 0.002%

    No Known Activations