© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11514
    Prev
    Next
    INDEX
    Explanations

    counting, conditions, loops, boundary checks

    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
    䒑
    2.84
    湁
    2.70
    आती
    2.63
    าวิ
    2.56
    垀
    2.50
    та
    2.48
    ल्टा
    2.47
    
    2.44
    म्प्ट
    2.42
    ExpNow
    2.42
    POSITIVE LOGITS
    EST
    1.84
    ej
    1.84
    est
    1.74
    নের
    1.70
     जना
    1.69
    ற்ற
    1.68
    quele
    1.64
    ead
    1.60
    ற்று
    1.57
     Don
    1.56
    Activations Density 0.034%

    No Known Activations