© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8050
    Prev
    Next
    INDEX
    Explanations

    finding support or paths

    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_22_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
    (
    0.97
    using
    0.97
     TMD
    0.89
    //
    0.88
     '(
    0.83
    치는
    0.81
     ('
    0.80
     '
    0.80
     aand
    0.78
    amd
    0.77
    POSITIVE LOGITS
     abajo
    1.03
     defesa
    1.02
     защи
    1.01
     ослож
    1.00
     खी
    0.98
     numerosos
    0.98
    convén
    0.98
    мян
    0.98
    返
    0.98
    ně
    0.98
    Activations Density 0.001%

    No Known Activations