© 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. 13599
    Prev
    Next
    INDEX
    Explanations

    unlimited number, only one

    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
    ing
    2.25
    Stay
    2.15
    ー
    2.02
    e
    1.98
     Stay
    1.98
    er
    1.98
    and
    1.97
    ed
    1.94
    ી
    1.91
    i
    1.87
    POSITIVE LOGITS
    ácie
    2.16
    賊
    2.11
    
    2.10
    दिग्ध
    2.08
    $('.
    2.07
    ovaž
    2.06
    玫
    1.96
    rasz
    1.93
    ذاء
    1.89
     Prozent
    1.89
    Activations Density 0.000%

    No Known Activations