© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 683
    Prev
    Next
    INDEX
    Explanations

    conjunctions and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    Durch
    0.57
    र्यंत
    0.57
    İŞ
    0.56
    軀
    0.56
    ترك
    0.55
    చ్చ
    0.54
    Så
    0.53
    Muchas
    0.53
    ฯ
    0.53
     সম্পর্
    0.52
    POSITIVE LOGITS
     ಮತ್ತು
    0.62
     ਅਤੇ
    0.56
     һәм
    0.54
     ಹಾಗೂ
    0.50
     deleg
    0.49
     மற்றும்
    0.48
    ancellationToken
    0.47
     agus
    0.47
     және
    0.47
     fundador
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.