© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    sequences indicating definition or continuation

    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_9_width_262k_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
     presc
    1.35
    لوم
    1.21
    
    1.18
     aquesta
    1.16
    я
    1.15
     trasp
    1.13
    <unused378>
    1.13
    ∈</
    1.12
     FSH
    1.12
    <unused1992>
    1.11
    POSITIVE LOGITS
    res
    1.22
    thing
    1.20
    settings
    1.12
    plitude
    1.06
    sp
    1.04
    órz
    1.03
    bed
    1.00
    လီ
    0.99
    icore
    0.99
    𝚊
    0.99
    Activations Density 0.000%

    No Known Activations