© 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. 8538
    Prev
    Next
    INDEX
    Explanations

    css border color like #ccc

    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
    ಚಿತ
    1.18
    蟠
    1.17
    儁
    1.13
    เอียด
    1.12
    freie
    1.12
    aacute
    1.12
    amis
    1.11
    érie
    1.11
    remain
    1.10
    覦
    1.09
    POSITIVE LOGITS
     net
    1.09
     Net
    1.08
    Net
    0.89
     trang
    0.87
    後の
    0.87
     part
    0.87
     సై
    0.86
    回の
    0.85
     తెలంగాణ
    0.84
    ালি
    0.84
    Activations Density 0.002%

    No Known Activations