© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11023
    Prev
    Next
    INDEX
    Explanations

    walking is great

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     house
    0.44
     drive
    0.42
    ドライブ
    0.39
    霄
    0.39
     Drive
    0.38
     Fahrt
    0.38
     houses
    0.37
    House
    0.37
     drives
    0.37
    house
    0.36
    POSITIVE LOGITS
    Exploring
    0.47
     Exploring
    0.46
     explorar
    0.46
     distances
    0.46
     exploring
    0.46
     supplemented
    0.45
     portions
    0.45
    able
    0.43
    🚶
    0.43
     extensively
    0.41
    Activations Density 0.009%

    No Known Activations