© 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. 9756
    Prev
    Next
    INDEX
    Explanations

    could you

    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
     তারাই
    0.85
    :^(
    0.85
     unchallenged
    0.84
    touches
    0.81
     パンツ
    0.80
     प्राधिकरण
    0.80
    ClickListener
    0.80
     गोनी
    0.79
    тории
    0.78
    POSITIVE LOGITS
     प्रण
    0.85
    桁
    0.83
    🦊
    0.80
    Notation
    0.80
     Cora
    0.79
    campo
    0.79
    pfl
    0.78
    letter
    0.77
     स्वरुप
    0.77
     값
    0.77
    Activations Density 0.007%

    No Known Activations