© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    measurements ending in inches

    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
    垢
    1.02
    ИТ
    1.01
    estones
    0.97
    Concluding
    0.95
    ิจ
    0.94
    дится
    0.93
    дії
    0.92
    IUM
    0.92
    ρίζ
    0.92
    END
    0.91
    POSITIVE LOGITS
     Peral
    0.95
     disbelief
    0.89
     firearm
    0.84
     worst
    0.82
     compose
    0.80
    캬
    0.80
     hê
    0.79
     thoroughly
    0.78
     programação
    0.78
     பெயர்
    0.77
    Activations Density 0.015%

    No Known Activations