© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3963
    Prev
    Next
    INDEX
    Explanations

    highway and road names

    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_29_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
     অধ
    0.69
    zoa
    0.69
    徒歩
    0.68
     লো
    0.63
    த்தைச்
    0.63
    ürm
    0.62
    plexity
    0.62
     靴
    0.62
     पदार्थ
    0.62
    WithOwner
    0.61
    POSITIVE LOGITS
     Highway
    2.03
     Interstate
    1.96
     Hwy
    1.95
     highway
    1.92
    Highway
    1.89
     interstate
    1.73
    highway
    1.58
     freeway
    1.57
     highways
    1.55
     Highways
    1.44
    Activations Density 0.078%

    No Known Activations