© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    contains followed by nouns

    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
     У
    3.29
     Ле
    3.20
     При
    3.06
     Та
    2.98
     Са
    2.98
     Ти
    2.96
     Ви
    2.90
     Ли
    2.85
     По
    2.85
     Ч
    2.82
    POSITIVE LOGITS
     skute
    2.90
     gyakor
    2.84
    ங்கிணை
    2.79
     nabí
    2.59
     susah
    2.57
     trochu
    2.57
     jährlich
    2.54
     zcela
    2.52
     legjob
    2.52
     hauptsächlich
    2.45
    Activations Density 0.023%

    No Known Activations