© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 638
    Prev
    Next
    INDEX
    Explanations

    model response start

    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
    ingle
    0.83
    iction
    0.78
    মিক
    0.76
    INGLE
    0.73
     dast
    0.73
     কাগজে
    0.72
     sheeting
    0.71
    엡
    0.71
     imaginary
    0.71
     осигура
    0.71
    POSITIVE LOGITS
     Reply
    1.57
     Replies
    1.47
     Posted
    1.41
     replied
    1.40
     replies
    1.40
     comments
    1.35
     reply
    1.34
    comments
    1.34
     Comment
    1.33
     commenter
    1.32
    Activations Density 1.862%

    No Known Activations