© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1077
    Prev
    Next
    INDEX
    Explanations

    GPT models

    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
    ames
    2.04
    [(\
    2.02
    තුරු
    2.01
    na
    1.96
    ttes
    1.96
    ాన
    1.88
    rh
    1.83
    hooks
    1.82
     себя
    1.81
    nect
    1.78
    POSITIVE LOGITS
    跏
    2.68
     pracę
    2.64
     गला
    2.61
     zdoby
    2.57
    polit
    2.56
    hoven
    2.45
     tegas
    2.41
    ୍ୟ
    2.41
     wprowad
    2.40
     poved
    2.38
    Activations Density 0.092%

    No Known Activations