© 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. 7108
    Prev
    Next
    INDEX
    Explanations

    opening or launching

    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
     down
    0.93
     diminishes
    0.80
     اهمیت
    0.80
    瑟
    0.79
     vanishes
    0.77
    ulers
    0.77
    ើរ
    0.76
     destroys
    0.76
    ทำ
    0.76
     Kuznet
    0.75
    POSITIVE LOGITS
    billy
    0.95
    dad
    0.77
    chten
    0.76
     diph
    0.75
    amy
    0.74
    irme
    0.74
    enen
    0.72
    呼
    0.71
    ától
    0.71
    aplan
    0.71
    Activations Density 0.028%

    No Known Activations