© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7950
    Prev
    Next
    INDEX
    Explanations

    private and public keywords

    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
     不能
    1.37
     not
    1.34
     meta
    1.31
     跟
    1.31
     see
    1.31
     nay
    1.29
     cf
    1.28
     stay
    1.26
     preferably
    1.26
     특히
    1.24
    POSITIVE LOGITS
    (),
    1.33
    একটি
    1.29
    </h1>
    1.25
    परिषद
    1.24
    。「
    1.22
    वृद्धि
    1.21
     فونبټ
    1.19
    dokument
    1.18
    、「
    1.17
    Bluetooth
    1.17
    Activations Density 0.003%

    No Known Activations