© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    value proposition

    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
    @-
    0.87
     discarding
    0.79
    ាប
    0.79
    ्यान
    0.77
    percentages
    0.77
    剃
    0.77
    ение
    0.77
    igat
    0.77
    пы
    0.76
    핑
    0.75
    POSITIVE LOGITS
     paraît
    1.14
     appears
    1.05
     paraissent
    1.01
    되었습니다
    1.00
     ieri
    0.99
     входит
    0.98
     Bernard
    0.98
     dimanche
    0.97
    dür
    0.96
     mało
    0.96
    Activations Density 0.009%

    No Known Activations