© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14313
    Prev
    Next
    INDEX
    Explanations

    plot scatter points in code

    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
    genius
    1.44
    ans
    1.43
    as
    1.37
    osaur
    1.35
    ’
    1.34
    platz
    1.33
    usian
    1.31
    ¥
    1.31
    atomy
    1.28
     monstros
    1.28
    POSITIVE LOGITS
     vehículos
    1.80
     cultivos
    1.70
     Subsequently
    1.67
     parejas
    1.66
     viviendas
    1.64
     dicha
    1.64
    躇
    1.62
     souhaitez
    1.61
     vehículo
    1.61
     suelo
    1.61
    Activations Density 0.083%

    No Known Activations