© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57060
    Prev
    Next
    INDEX
    Explanations

    butter and melting

    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_all/layer_41_width_262k_l0_big
    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
    SOFT
    0.46
    软
    0.44
     softened
    0.43
     SOFT
    0.40
    Soft
    0.38
     мяг
    0.37
     cuáles
    0.37
     अधू
    0.37
     অবরোধ
    0.37
     Simulate
    0.37
    POSITIVE LOGITS
    Butter
    0.89
    butter
    0.87
     butter
    0.87
     Butter
    0.81
    バター
    0.72
    🧈
    0.71
     beurre
    0.70
     melted
    0.66
     Melting
    0.66
     melting
    0.65
    Activations Density 0.006%

    No Known Activations