© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    you how

    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
    촤
    1.11
    शहर
    1.05
    방법
    1.04
    暧
    1.03
     رک
    1.02
    ással
    1.02
    Рис
    1.01
    Rather
    1.01
    radioButton
    0.96
    曖
    0.96
    POSITIVE LOGITS
     crowd
    0.93
     sounding
    0.93
     gent
    0.92
     dig
    0.91
     hump
    0.90
     nobles
    0.90
     upper
    0.89
     antiqu
    0.89
     jug
    0.89
    гү
    0.89
    Activations Density 0.000%

    No Known Activations