© 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. 8532
    Prev
    Next
    INDEX
    Explanations

    sequences starting with specific tokens

    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
     Cuc
    1.19
     Benoit
    1.19
     cuc
    1.18
     CAC
    1.16
    鄢
    1.09
     CDT
    1.06
     Colombe
    1.05
     Ziegler
    1.05
     prolog
    1.05
    舅
    1.05
    POSITIVE LOGITS
     SH
    3.00
    Shaw
    2.92
     Shaw
    2.89
    SH
    2.87
     Shar
    2.85
    Shar
    2.81
    Sh
    2.74
    Sha
    2.70
     Sh
    2.66
     Shak
    2.65
    Activations Density 1.539%

    No Known Activations