© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9732
    Prev
    Next
    INDEX
    Explanations

    no management or infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     enga
    0.90
    र्फ
    0.89
     occasionally
    0.88
    rokken
    0.86
    Occasionally
    0.86
    憾
    0.85
    kort
    0.85
    Итак
    0.84
    pé
    0.84
     斜
    0.84
    POSITIVE LOGITS
     costs
    1.03
    成本
    0.98
     Would
    0.98
     WOULD
    0.94
     Costs
    0.94
     would
    0.93
     coûte
    0.92
    would
    0.91
     COSTS
    0.90
     armado
    0.90
    Activations Density 0.290%

    No Known Activations