© 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. 931
    Prev
    Next
    INDEX
    Explanations

    php database code statements

    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
    <bos>
    2.60
     raises
    1.86
    ⎣
    1.80
     kicks
    1.75
     ghosts
    1.75
     sockets
    1.74
    ogenesis
    1.74
     consecutively
    1.73
     incidentally
    1.72
    noon
    1.70
    POSITIVE LOGITS
     conectar
    2.18
    Ц
    2.12
    eszcze
    2.09
    σότε
    2.03
    ాన్ని
    1.99
    guồn
    1.96
    áu
    1.95
     zákon
    1.91
    Њ
    1.91
    会有
    1.91
    Activations Density 0.056%

    No Known Activations