© 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. 961
    Prev
    Next
    INDEX
    Explanations

    submissive names and terms

    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
     encabez
    1.86
     पूछी
    1.85
     compd
    1.84
    ྜ
    1.83
     facilidad
    1.79
    बाइल
    1.78
    फेक्ट
    1.77
     provved
    1.77
     efic
    1.76
     percentuale
    1.75
    POSITIVE LOGITS
    ppling
    1.33
    ه
    1.30
    a
    1.28
    hew
    1.22
     k
    1.20
     onwards
    1.12
     reach
    1.12
    اريخ
    1.10
     و
    1.08
    aing
    1.07
    Activations Density 0.306%

    No Known Activations