© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8928
    Prev
    Next
    INDEX
    Explanations

    table separators

    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
     (‘
    2.71
     ('
    2.58
     (`
    2.14
     («
    2.11
     (’
    2.06
    」(
    2.03
     (/
    2.01
    ('%
    1.99
     (
    1.99
     (&
    1.97
    POSITIVE LOGITS
     uh
    2.59
     yeah
    2.14
     Yeah
    1.97
     um
    1.78
     kind
    1.78
     cuz
    1.76
     gonna
    1.73
    yeah
    1.68
    Yeah
    1.66
     sort
    1.65
    Activations Density 0.477%

    No Known Activations