© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13888
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    Nicola
    1.15
    enzel
    1.06
     Robert
    1.02
    也就是
    1.02
     Gilbert
    1.01
    Bruno
    1.00
    <strong>
    1.00
    或是
    0.99
    Robert
    0.97
    Bruce
    0.94
    POSITIVE LOGITS
    ༩
    1.66
    <0xF3>
    1.65
    »),
    1.64
    ”
    1.63
    ultaneous
    1.63
     \"%
    1.62
     субъек
    1.60
    _{+}
    1.60
    )‏
    1.58
     கட்ச
    1.58
    Activations Density 0.012%

    No Known Activations