© 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. 32792
    Prev
    Next
    INDEX
    Explanations

    traversing pathways

    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
    ே
    0.48
    ิ
    0.46
    ை
    0.45
     natthi
    0.43
    چی
    0.43
     દૂર
    0.42
    ｐ
    0.42
     எதுவும்
    0.42
     volto
    0.42
    m
    0.41
    POSITIVE LOGITS
     tunnels
    0.64
     veins
    0.61
     ranks
    0.59
     rapids
    0.59
     channels
    0.58
     canyons
    0.57
     motions
    0.57
     checkpoints
    0.54
    zech
    0.53
     arteries
    0.53
    Activations Density 0.016%

    No Known Activations