© 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. 810
    Prev
    Next
    INDEX
    Explanations

    markdown links

    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
    های
    1.33
    り
    1.31
    ピュー
    1.30
    …
    1.29
    ۲
    1.28
     samping
    1.27
    ઓ
    1.25
    quelle
    1.25
    ..
    1.22
     soleil
    1.21
    POSITIVE LOGITS
    leadsto
    1.95
    hfill
    1.90
    POSITORY
    1.87
    micronaut
    1.84
    OCATION
    1.84
    asible
    1.83
    itemView
    1.83
    shims
    1.82
    ্টন
    1.82
    ի
    1.81
    Activations Density 1.338%

    No Known Activations