© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7881
    Prev
    Next
    INDEX
    Explanations

    print, fotografi, less, teammate, очень, json, hyd

    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
    尉
    0.96
     devoting
    0.94
     sacrificing
    0.93
     requiring
    0.92
     removing
    0.91
     말씀을
    0.87
     phr
    0.87
     legislate
    0.87
     expressing
    0.86
     presenting
    0.86
    POSITIVE LOGITS
    靓
    1.01
    casian
    0.94
     русской
    0.93
     Valentina
    0.91
     disco
    0.91
    Diamond
    0.87
     vállalat
    0.87
     chubby
    0.87
    챱
    0.87
     ragazza
    0.87
    Activations Density 0.000%

    No Known Activations