© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146308
    Prev
    Next
    INDEX
    Explanations

    adhesion, cohesion, capillary action

    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_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
    馄
    0.78
    િજા
    0.78
     साइबर
    0.73
    တို့
    0.73
    ipan
    0.70
     Shu
    0.70
    Cha
    0.70
     exchanges
    0.69
    长安
    0.69
    鸳
    0.69
    POSITIVE LOGITS
     adhesion
    0.91
     cohesion
    0.80
     adhesive
    0.79
     Adhesive
    0.73
     cohesive
    0.72
     Ad
    0.69
    cap
    0.68
     backbone
    0.68
     Cap
    0.66
     adhes
    0.64
    Activations Density 0.003%

    No Known Activations