© 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. 13610
    Prev
    Next
    INDEX
    Explanations

    css centering

    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
    ையை
    1.78
    chromium
    1.65
     দেশটি
    1.65
     iremos
    1.63
     পাকিস্তানীরা
    1.59
     děti
    1.57
     recebe
    1.57
    쬐
    1.55
     podej
    1.53
     demostrado
    1.52
    POSITIVE LOGITS
     belongings
    1.31
     congreg
    1.29
     temporary
    1.24
     item
    1.19
     billing
    1.14
     HUM
    1.14
     items
    1.12
     courteous
    1.11
    ట్‌
    1.08
     impromptu
    1.07
    Activations Density 0.028%

    No Known Activations