© 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. 11250
    Prev
    Next
    INDEX
    Explanations

    mixed language detection

    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
    窕
    2.84
    memberNameLink
    2.80
    逅
    2.57
     declare
    2.45
    MENT
    2.39
    HING
    2.37
    蜍
    2.34
     evade
    2.33
     chase
    2.31
     segue
    2.30
    POSITIVE LOGITS
    <bos>
    2.68
    jenja
    2.59
    علم
    2.52
    ementia
    2.51
    ar
    2.47
    čenje
    2.38
    ل
    2.38
     '''
    2.32
    emort
    2.30
    aczego
    2.30
    Activations Density 0.011%

    No Known Activations