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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 98704
    Prev
    Next
    INDEX
    Explanations

    eating and being eaten

    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
     Anton
    0.40
     whiskey
    0.40
     احتجاج
    0.38
    obarbital
    0.38
     stubborn
    0.37
     పరుగులు
    0.37
    汼
    0.37
     embarrassment
    0.36
     Orthodox
    0.36
     goof
    0.36
    POSITIVE LOGITS
     devoured
    1.27
     devour
    1.23
     cannibal
    1.22
     eaten
    1.07
    吃了
    1.02
    吞
    0.95
     eating
    0.93
    吃
    0.93
     eats
    0.91
    eating
    0.89
    Activations Density 0.053%

    No Known Activations