© 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. 11489
    Prev
    Next
    INDEX
    Explanations

    hoo, shoes, hen

    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
    kmale
    2.45
    psin
    2.34
    ("|
    2.33
    ('|
    2.25
    ("-
    2.22
    pp
    2.19
    सेवी
    2.19
    ubov
    2.18
    pyplot
    2.15
    ري
    2.14
    POSITIVE LOGITS
    ும்
    3.06
    inio
    2.65
    िजन
    2.53
    រយៈពេល
    2.49
    ◸
    2.47
     ngành
    2.46
    บาท
    2.45
    hooter
    2.44
     occidentale
    2.41
    مند
    2.38
    Activations Density 0.019%

    No Known Activations