© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 29491
    Prev
    Next
    INDEX
    Explanations

    animal breeds and races

    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
     अनुभवी
    0.39
    凋
    0.38
     Goodman
    0.37
    (:
    0.37
    냇
    0.37
    둣
    0.36
     señora
    0.36
    痪
    0.36
     کمان
    0.35
    狀
    0.35
    POSITIVE LOGITS
     races
    1.63
     race
    1.63
    Race
    1.48
    race
    1.43
     Races
    1.43
     racial
    1.37
     Race
    1.35
     breed
    1.32
     breeds
    1.32
     RACE
    1.20
    Activations Density 0.029%

    No Known Activations