© 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. 7954
    Prev
    Next
    INDEX
    Explanations

    prices and costs

    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
     ९
    1.22
    ９
    1.17
     nearly
    1.11
     nine
    1.09
     девя
    1.08
     nineteen
    1.07
     ninety
    1.07
     nueve
    1.03
     Nearly
    0.99
    Nine
    0.99
    POSITIVE LOGITS
    梧
    0.86
    ඟ
    0.82
    稔
    0.81
    uble
    0.79
    歓迎
    0.79
    IZE
    0.79
     মাস্টার
    0.77
    璿
    0.77
    显
    0.76
    Acte
    0.76
    Activations Density 0.186%

    No Known Activations