© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3757
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     during
    0.89
     envisaged
    0.86
     visions
    0.84
    ukhov
    0.81
     sometime
    0.81
    ≳
    0.80
     theological
    0.80
     Schol
    0.79
     нередко
    0.78
    øy
    0.78
    POSITIVE LOGITS
    components
    0.90
    Components
    0.88
    whitespace
    0.74
    这个
    0.73
     components
    0.73
    为什么
    0.71
     бое
    0.71
    curly
    0.71
    l
    0.70
    طف
    0.70
    Activations Density 0.757%

    No Known Activations