© 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. 8872
    Prev
    Next
    INDEX
    Explanations

    wall art wallpapers Twenty Thai Boxing Hoverflies

    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
     Peek
    0.95
    nless
    0.91
    下さい
    0.90
    anne
    0.89
    نس
    0.89
    쩔
    0.88
    뭅
    0.87
    窝
    0.87
    ครัว
    0.86
     mida
    0.85
    POSITIVE LOGITS
     dollars
    1.24
     litres
    1.18
     tonnes
    1.15
     рублей
    1.10
     gigantes
    1.07
     pounds
    1.07
    tickets
    1.06
     annuities
    1.06
     ziff
    1.06
     cents
    1.06
    Activations Density 0.000%

    No Known Activations