© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9525
    Prev
    Next
    INDEX
    Explanations

    python class self initialization

    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
    oniazid
    1.19
     tarixində
    1.15
    rité
    1.09
     alcalde
    1.08
    歿
    1.08
    wych
    1.07
     fédéral
    1.06
    idio
    1.04
     arbeids
    1.04
    ត្តិ
    1.04
    POSITIVE LOGITS
     Then
    1.21
     This
    1.12
     However
    1.12
     But
    1.06
     For
    1.05
     Initially
    1.05
     Earlier
    1.04
     I
    1.03
     Use
    1.03
     Later
    1.02
    Activations Density 0.008%

    No Known Activations