© 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. 7553
    Prev
    Next
    INDEX
    Explanations

    email marketing

    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
     yurt
    0.91
     Delight
    0.82
     Ally
    0.80
    ៃ
    0.75
     ar
    0.74
     صغيرة
    0.73
    ;++
    0.71
    ್ಯಾ
    0.71
     Levit
    0.71
     felt
    0.71
    POSITIVE LOGITS
    獠
    1.12
    umas
    1.07
     resuscitation
    1.03
    sever
    1.02
     alcançar
    1.02
     নিরস্ত্র
    0.99
    visual
    0.98
     armas
    0.98
    ಹಾಸ
    0.97
    platform
    0.96
    Activations Density 0.001%

    No Known Activations