© 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. 998
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
     cl
    1.33
     h
    1.26
     d
    1.20
     z
    1.12
    ers
    1.07
    Z
    1.06
    ING
    1.05
    ing
    1.05
     m
    1.05
    wn
    1.02
    POSITIVE LOGITS
     atribu
    2.16
    麂
    1.93
    佹
    1.92
    道府県
    1.91
    มห
    1.88
    दीश
    1.88
     racionais
    1.88
     Оте
    1.87
     ferrugineux
    1.85
    蘑
    1.85
    Activations Density 0.162%

    No Known Activations