© 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. 9136
    Prev
    Next
    INDEX
    Explanations

    image and graph neural networks

    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
     Daryl
    0.92
     chạm
    0.89
     hypoth
    0.85
     интер
    0.84
     کہتے
    0.82
     yüzy
    0.82
     Brat
    0.80
    尝
    0.80
     certamente
    0.79
     arrib
    0.79
    POSITIVE LOGITS
    ening
    2.79
    ened
    2.56
    ENING
    2.32
    eners
    2.04
    ens
    2.02
    ener
    1.92
    enen
    1.90
    enes
    1.78
    ENER
    1.67
    en
    1.67
    Activations Density 0.156%

    No Known Activations