© 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. 8310
    Prev
    Next
    INDEX
    Explanations

    socialist republic or one-party state

    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
     condo
    0.99
     aclar
    0.95
    (':')[
    0.95
    냥
    0.92
     dair
    0.92
     contrace
    0.91
     alimentation
    0.90
     manej
    0.90
     soy
    0.89
     conference
    0.89
    POSITIVE LOGITS
    <0x84>
    1.07
    örd
    1.01
     NotImplemented
    1.00
     Die
    1.00
     ધો
    0.99
    ög
    0.98
     સિ
    0.97
    рах
    0.94
     Marino
    0.94
     Myst
    0.94
    Activations Density 0.000%

    No Known Activations