© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8552
    Prev
    Next
    INDEX
    Explanations

    Go import statements

    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_13_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
     食
    2.23
     做
    2.03
    做
    2.03
    лама
    1.94
     uptick
    1.89
     无
    1.87
    撒
    1.87
     死
    1.85
     nays
    1.85
     incarceration
    1.84
    POSITIVE LOGITS
     variante
    2.47
     interessante
    2.40
     europ
    2.39
     vier
    2.36
     ä
    2.36
     hier
    2.35
     homogene
    2.34
     konkre
    2.33
     elektron
    2.32
     sensibil
    2.31
    Activations Density 1.845%

    No Known Activations