© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 265
    Prev
    Next
    INDEX
    Explanations

    -W flags and their meanings

    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
    busters
    1.33
    ument
    1.18
    final
    1.13
    _
    1.06
    buster
    1.06
    seekBar
    1.05
    Farmers
    1.02
    age
    1.01
    father
    1.00
    quota
    0.99
    POSITIVE LOGITS
    лая
    1.93
     hầu
    1.85
     连接
    1.83
    лые
    1.83
     多く
    1.82
     Specimens
    1.77
    <unused715>
    1.73
     Particularly
    1.72
     तस्वी
    1.72
    ᾷ
    1.72
    Activations Density 0.037%

    No Known Activations