© 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. 2400
    Prev
    Next
    INDEX
    Explanations

    dairy and oils

    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
    szer
    2.08
     மீண்டும்
    2.08
     clos
    1.98
     질
    1.96
    y
    1.95
    $/.
    1.92
     무
    1.92
    廃
    1.92
    ঝ
    1.91
    깊
    1.90
    POSITIVE LOGITS
    ptic
    1.90
    ewhat
    1.83
    ंपरा
    1.81
    以往
    1.75
    </img>
    1.73
     Ради
    1.73
    āya
    1.73
    aiser
    1.71
    inink
    1.69
     admitting
    1.69
    Activations Density 0.377%

    No Known Activations