© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    json keys and labels

    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
    !;
    1.30
    ;')
    1.25
    ;)
    1.24
    =*
    1.23
    ?;
    1.17
    !?
    1.17
    !
    1.15
    !!
    1.15
    =!
    1.14
    !')
    1.14
    POSITIVE LOGITS
    ":
    1.74
    ”:
    1.23
    ":{"
    1.17
    \":
    1.15
    ":[
    1.12
    ':
    1.10
     ":
    1.04
    »:
    0.99
    ":"",
    0.97
    ":"
    0.95
    Activations Density 0.018%

    No Known Activations