© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7092
    Prev
    Next
    INDEX
    Explanations

    adjective and adverb endings

    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_22_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
    erial
    0.83
     Ded
    0.81
    tert
    0.81
    bald
    0.80
    chts
    0.80
    ball
    0.79
     간
    0.77
    بي
    0.76
    teren
    0.75
     داد
    0.75
    POSITIVE LOGITS
    ously
    2.35
    OUS
    2.02
    ous
    1.96
    iously
    1.87
    oust
    1.75
    uos
    1.72
    OSO
    1.71
    osos
    1.69
    uous
    1.69
    ioso
    1.69
    Activations Density 0.122%

    No Known Activations