Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 6029
    Prev
    Next
    INDEX
    Explanations

    ropes, cables, and chains

    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
     bake
    0.89
    铣
    0.80
     Bake
    0.79
    🥧
    0.78
    扫描
    0.77
     Baked
    0.74
    Stamp
    0.73
    🍰
    0.73
    baked
    0.73
    碉
    0.73
    POSITIVE LOGITS
     rope
    2.58
     ropes
    2.44
     Rope
    2.16
     cable
    2.10
     cables
    2.09
     cords
    1.99
     cord
    1.99
     corde
    1.96
    绳
    1.89
     Cable
    1.86
    Activations Density 0.237%

    No Known Activations