© 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. 10620
    Prev
    Next
    INDEX
    Explanations

    can I followed by help

    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
    jetbrains
    1.17
    ارش
    1.13
     SHOULD
    1.11
    툼
    1.04
    ftop
    1.03
    ார்க்க
    1.02
     precludes
    1.02
     (\<
    1.02
    marquee
    1.02
     COULD
    1.01
    POSITIVE LOGITS
    u
    0.96
     mais
    0.91
    が
    0.90
     ayer
    0.89
     meer
    0.88
     bijna
    0.88
     almost
    0.87
     u
    0.87
    たち
    0.86
    و
    0.85
    Activations Density 0.010%

    No Known Activations