© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2280
    Prev
    Next
    INDEX
    Explanations

    innovation and approach

    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
    ungan
    2.05
    ँच
    2.03
     e
    2.02
     n
    1.95
    umber
    1.95
    ubs
    1.90
     MEAN
    1.89
     GTP
    1.89
    །
    1.89
     TE
    1.85
    POSITIVE LOGITS
    تور
    2.82
    تدائي
    2.74
    ليه
    2.67
    ો
    2.57
    銈
    2.54
    ඪ
    2.47
     reincarnation
    2.47
    ObjectName
    2.45
    klass
    2.44
    িং
    2.44
    Activations Density 0.192%

    No Known Activations