© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12219
    Prev
    Next
    INDEX
    Explanations

    confidence score

    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
    ემა
    2.71
    ுள்ள
    2.69
    ுள்ளார்
    2.61
    ى
    2.60
     اعلی
    2.58
    어로
    2.50
     गेल्या
    2.49
    PING
    2.45
    ंपरा
    2.45
    াপনের
    2.45
    POSITIVE LOGITS
     Nes
    2.26
     quebr
    2.19
     bearing
    2.14
     breakup
    2.07
    FAI
    2.06
     descanso
    2.05
     deposed
    1.98
    Whole
    1.96
    h
    1.95
     weather
    1.95
    Activations Density 0.028%

    No Known Activations