© 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. 14777
    Prev
    Next
    INDEX
    Explanations

    package manager

    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
     Сте
    1.48
    軹
    1.47
     wilayah
    1.37
     また
    1.36
     போல்
    1.35
    ㅛ
    1.35
    ˍ
    1.32
     وتم
    1.30
    />}/>
    1.30
     وقال
    1.30
    POSITIVE LOGITS
    챙
    1.06
     bouillon
    1.04
    Certified
    1.00
     handbag
    0.98
     duly
    0.98
    يدك
    0.95
     ấy
    0.94
     tut
    0.93
     properly
    0.91
    ็อก
    0.91
    Activations Density 0.272%

    No Known Activations