© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 900
    Prev
    Next
    INDEX
    Explanations

    starts numbered lists with 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     here
    0.84
    <unused1691>
    0.78
    <unused2140>
    0.76
    <unused2113>
    0.72
     까지
    0.68
    ņ
    0.67
    spaceBetween
    0.66
     यहाँ
    0.66
    <unused2222>
    0.65
    itance
    0.65
    POSITIVE LOGITS
    1
    1.93
    1.51
    ১
    1.34
     ١
    1.25
    １
    1.24
    १
    1.24
    ١
    1.24
     ১
    1.22
     ૧
    1.18
    A
    1.10
    Activations Density 1.078%

    No Known Activations