© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    sharks and predators

    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_31_width_65k_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
     پرویز
    0.46
    лянчук
    0.46
    👬
    0.45
    㗊
    0.41
    ᆯ
    0.41
     switchTo
    0.40
    ปร
    0.40
    Links
    0.40
    Firebase
    0.39
    Setting
    0.39
    POSITIVE LOGITS
     shark
    1.02
     sharks
    0.94
     predators
    0.75
     Shark
    0.75
     predator
    0.73
     Sharks
    0.72
    鯊
    0.72
    shark
    0.70
    Shark
    0.68
     jaws
    0.67
    Activations Density 0.083%

    No Known Activations