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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6133
    Prev
    Next
    INDEX
    Explanations

    street and road networks

    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_22_width_65k_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
     doorbell
    1.01
    ه
    0.96
    tım
    0.93
    ীয়
    0.92
    डल
    0.92
     مدار
    0.92
    <0x0D>
    0.91
    𝚎
    0.90
     flywheel
    0.90
    <unused4>
    0.89
    POSITIVE LOGITS
    徑
    1.32
    WAYS
    1.22
    ways
    1.16
    finders
    1.13
    WAY
    1.12
     المستقيم
    1.09
     facendo
    1.05
    finding
    1.04
     длиной
    1.04
    褴
    1.04
    Activations Density 0.173%

    No Known Activations