© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2589
    Prev
    Next
    INDEX
    Explanations

    worn, damaged, or aged objects

    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
     亻
    0.36
    一定的
    0.36
     appreciable
    0.35
     Importantly
    0.35
     conducive
    0.35
    <unused2130>
    0.35
    嶠
    0.34
    <unused2164>
    0.34
     workmanship
    0.34
     belangrijk
    0.34
    POSITIVE LOGITS
     drunken
    0.62
     sweaty
    0.60
     dusty
    0.60
     gritty
    0.58
     soggy
    0.58
     greasy
    0.57
     rusty
    0.57
     jagged
    0.57
     cynical
    0.56
     rusted
    0.56
    Activations Density 0.062%

    No Known Activations