© 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. 6979
    Prev
    Next
    INDEX
    Explanations

    official project documentation and forums

    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
     نحو
    0.81
     ambos
    0.79
    abez
    0.78
    orm
    0.78
    abdomen
    0.76
    λλη
    0.75
    ['_
    0.75
    '*
    0.74
     কামাল
    0.74
     জিয়া
    0.72
    POSITIVE LOGITS
    jillo
    0.98
    ispiel
    0.89
     그런
    0.87
    Fernseh
    0.85
    DejaVu
    0.84
     Parton
    0.81
    pah
    0.81
    ro
    0.81
    ట్ల
    0.80
    そういう
    0.80
    Activations Density 0.063%

    No Known Activations