© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    sponsor remunerations

    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
    flor
    1.83
    Bridge
    1.72
    扫
    1.70
    ốc
    1.69
    deb
    1.67
     זאת
    1.67
    ंत
    1.66
    serious
    1.62
    VO
    1.61
     gone
    1.60
    POSITIVE LOGITS
    aneswar
    1.61
    OURCES
    1.58
     */
    1.57
     \*
    1.54
     vaginalis
    1.51
     (?)
    1.51
    RUPTION
    1.50
    hapi
    1.50
     epig
    1.48
     jdbc
    1.47
    Activations Density 0.000%

    No Known Activations