© 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. 1264
    Prev
    Next
    INDEX
    Explanations

    hsa

    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
    िकन
    2.30
    ratingBarStyle
    2.25
    ឡិចត្រូ
    2.22
     "****
    2.22
    ಷ್ಟ
    2.22
    KeepOriginal
    2.20
    ည့်
    2.19
    мата
    2.18
     আকাঙ্
    2.17
     "|
    2.16
    POSITIVE LOGITS
    s
    2.58
    breadcrumbs
    2.05
     It
    1.90
    UE
    1.90
    COVID
    1.89
    ườn
    1.89
     nói
    1.87
     COVID
    1.87
    线
    1.86
     with
    1.85
    Activations Density 0.120%

    No Known Activations