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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1166
    Prev
    Next
    INDEX
    Explanations

    file paths and commands

    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
     ![
    2.69
     ㅣ
    2.55
     picked
    2.50
     (**
    2.45
     pick
    2.45
     `'
    2.44
     (`
    2.34
     [*
    2.34
     `#
    2.31
     [`
    2.30
    POSITIVE LOGITS
    alex
    2.55
    sweet
    2.54
    annotation
    2.54
    a
    2.52
    forums
    2.50
    funciones
    2.47
    modelo
    2.46
    ओ
    2.45
    लान
    2.43
    backpack
    2.42
    Activations Density 0.185%

    No Known Activations