© 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. 12612
    Prev
    Next
    INDEX
    Explanations

    don't feel pressured to

    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
    <bos>
    3.75
    ੴ
    2.96
     "/"
    2.86
    勮
    2.77
    idded
    2.60
    ابه
    2.54
    ॰ऍ
    2.54
    చిత
    2.53
    ೋಜನ
    2.53
    чете
    2.52
    POSITIVE LOGITS
    ಳ್
    2.65
    en
    2.49
    er
    2.48
     kalt
    2.47
    alist
    2.47
     giới
    2.42
    े
    2.38
    ക്ഷ
    2.30
    ا
    2.28
     불구하고
    2.24
    Activations Density 0.006%

    No Known Activations