© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11404
    Prev
    Next
    INDEX
    Explanations

    mixed language usage

    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
     agre
    2.18
    ised
    1.87
     campe
    1.86
    ̣
    1.85
     tog
    1.81
    vill
    1.70
    ುನ
    1.64
    ara
    1.61
    vote
    1.57
     insert
    1.57
    POSITIVE LOGITS
    ছেন
    2.06
    es
    2.05
    liness
    2.03
    弛
    2.03
     natoque
    1.95
    gbm
    1.92
    esm
    1.89
     vacated
    1.89
    वय
    1.85
    𓏸
    1.84
    Activations Density 0.000%

    No Known Activations