© 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. 9279
    Prev
    Next
    INDEX
    Explanations

    tokenizer, optimizer, loss

    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
     Mariana
    1.20
     plataformas
    1.12
     Normandie
    1.08
     Rocha
    1.07
     সফ
    1.05
     portes
    1.03
    Legal
    1.01
    坟
    1.00
     Roc
    1.00
     Maxime
    0.99
    POSITIVE LOGITS
     Item
    1.86
     ITEM
    1.81
    item
    1.73
    Item
    1.73
     item
    1.71
     ViewHolder
    1.68
     Items
    1.67
     items
    1.62
    ITEM
    1.60
    ViewHolder
    1.56
    Activations Density 0.196%

    No Known Activations