© 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. 9002
    Prev
    Next
    INDEX
    Explanations

    important notes and lists

    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
     cánh
    0.85
     Choice
    0.81
    igar
    0.76
     achievement
    0.76
    icult
    0.75
    墻
    0.74
     Accord
    0.72
    FieldValue
    0.71
    たつ
    0.71
    >());
    0.70
    POSITIVE LOGITS
     bottom
    1.06
     top
    1.02
     BOTTOM
    0.98
    Top
    0.97
    top
    0.96
    追加
    0.95
     bottoms
    0.94
    bottom
    0.94
     tops
    0.93
    sixth
    0.93
    Activations Density 0.078%

    No Known Activations