© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    this. followed by property

    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
    šo
    2.10
    oitte
    2.05
    šti
    2.02
    braska
    2.02
    <bos>
    1.99
    iš
    1.93
    бні
    1.92
     ناف
    1.91
    luğu
    1.91
    šia
    1.90
    POSITIVE LOGITS
    रा
    2.78
    FileChooser
    2.57
    ,\,\,\,\
    2.49
    CET
    2.41
    :'],
    2.41
    thiophen
    2.40
    benzoic
    2.37
    scriptsize
    2.37
    urized
    2.37
    ]{
    2.34
    Activations Density 0.026%

    No Known Activations