© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2218
    Prev
    Next
    INDEX
    Explanations

    million-dollar questions

    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
    -
    1.52
     K
    1.50
    ­
    1.44
     and
    1.40
    </b>
    1.39
    ’
    1.33
     witnessed
    1.31
     commit
    1.31
     played
    1.28
    </h4>
    1.27
    POSITIVE LOGITS
    skcipher
    1.89
    ብስብ
    1.72
    Antaeotricha
    1.71
    webserv
    1.69
    ڦ
    1.69
    calories
    1.69
    <unused1821>
    1.66
    Kamol
    1.66
    hiqdev
    1.66
    Therates
    1.66
    Activations Density 0.092%

    No Known Activations