© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9955
    Prev
    Next
    INDEX
    Explanations

    offering resources for struggles

    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
    ynski
    1.03
    ين
    0.96
    ા
    0.95
    らに
    0.93
    ownic
    0.93
    lys
    0.93
    ภั
    0.92
     Kern
    0.92
    ulman
    0.91
    வதில்
    0.91
    POSITIVE LOGITS
    言
    0.92
    atres
    0.90
     erle
    0.90
    sac
    0.87
    Sac
    0.87
    CEST
    0.82
     teórico
    0.82
    yenne
    0.81
     estere
    0.80
    Property
    0.80
    Activations Density 0.007%

    No Known Activations