© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109898
    Prev
    Next
    INDEX
    Explanations

    food scraps and garbage

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases related to animals and food or consumption, particularly in contexts about pests, wildlife, or eating habits.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tong
    -0.82
     Ballroom
    -0.81
    frow
    -0.80
    olisian
    -0.78
    cjon
    -0.77
    тивний
    -0.77
    oden
    -0.77
     eius
    -0.76
    ORD
    -0.75
    MOD
    -0.74
    POSITIVE LOGITS
     food
    1.74
     garbage
    1.52
     trash
    1.30
    garbage
    1.27
    food
    1.22
    Food
    1.19
     attract
    1.18
     Food
    1.13
     Garbage
    1.09
     FOOD
    1.05
    Activations Density 0.022%

    No Known Activations