© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17414
    Prev
    Next
    INDEX
    Explanations

    sheep and goats

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

    goat, sheep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     airfoil
    0.42
    彗
    0.42
    娉
    0.42
    쥘
    0.41
     Florida
    0.41
    Elena
    0.41
     parallax
    0.40
     Sasuke
    0.39
     பயணி
    0.39
    Florida
    0.38
    POSITIVE LOGITS
     goat
    3.52
     goats
    3.48
     sheep
    3.39
    羊
    3.36
     Sheep
    3.27
     Goat
    3.19
    Sheep
    3.16
    sheep
    3.13
    goat
    3.00
    🐑
    2.67
    Activations Density 0.069%

    No Known Activations