© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1051
    Prev
    Next
    INDEX
    Explanations

    helpful and harmless purpose

    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
     갖
    0.76
    aturation
    0.73
    тім
    0.73
     catch
    0.72
     catches
    0.72
    ті
    0.69
    нец
    0.68
    뜰
    0.68
    hé
    0.67
    MenuItemView
    0.67
    POSITIVE LOGITS
     Kaw
    0.75
     bằng
    0.74
     Wand
    0.74
     Pamp
    0.74
     pand
    0.72
    ಿಸ್
    0.70
     paws
    0.67
     आईआई
    0.66
    爪
    0.66
     Pah
    0.66
    Activations Density 0.507%

    No Known Activations