© 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. 8348
    Prev
    Next
    INDEX
    Explanations

    few followed by quantities or units

    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
     hoặc
    1.06
    -/
    1.06
    7
    1.03
     или
    1.02
    または
    1.01
    6
    0.99
     целях
    0.98
     либо
    0.98
    9
    0.97
     teljes
    0.96
    POSITIVE LOGITS
     hundred
    2.35
     thousand
    1.92
     dozen
    1.85
     weeks
    1.68
    hundred
    1.61
    thousand
    1.59
     hundert
    1.54
     millimeters
    1.52
     tenths
    1.52
    Hundred
    1.48
    Activations Density 0.119%

    No Known Activations