© 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. 9869
    Prev
    Next
    INDEX
    Explanations

    except Exception as

    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
    pliance
    1.09
     Bored
    1.08
     PBC
    1.07
    PBC
    1.07
     करूं
    1.07
     Reducing
    1.07
     বললে
    1.07
    ၞ
    1.03
     retelling
    1.02
     Forming
    1.02
    POSITIVE LOGITS
     인
    0.80
    刀
    0.71
     daz
    0.70
     پید
    0.68
    quisa
    0.67
     налич
    0.66
     각각
    0.65
    괜
    0.65
    흑
    0.65
     квадра
    0.65
    Activations Density 0.003%

    No Known Activations