© 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. 257
    Prev
    Next
    INDEX
    Explanations

    meticulous daily activities

    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
    ಳ
    1.94
     verdana
    1.88
     Mutter
    1.87
     Bên
    1.87
     bahagian
    1.87
     daimyo
    1.86
    geoType
    1.85
     anod
    1.85
     squadra
    1.84
     chiếc
    1.83
    POSITIVE LOGITS
    о
    1.45
    相应的
    1.38
    uming
    1.37
    differ
    1.32
    не
    1.32
    প
    1.31
    previous
    1.29
    ви
    1.29
    limited
    1.29
    reate
    1.29
    Activations Density 0.000%

    No Known Activations