© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1031
    Prev
    Next
    INDEX
    Explanations

    take text or advice

    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_7_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
    ্টার
    2.91
    शाली
    2.69
    кция
    2.67
     जोड़ा
    2.64
    ోతి
    2.64
    鄱
    2.63
    lanan
    2.55
    wght
    2.52
     tipped
    2.52
    ்ட்
    2.52
    POSITIVE LOGITS
    
    2.88
     place
    2.78
    ﺮ
    2.76
    place
    2.75
    
    2.65
    
    2.55
    শীল
    2.53
    %","
    2.42
    
    2.41
    falls
    2.38
    Activations Density 0.282%

    No Known Activations