Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12517
    Prev
    Next
    INDEX
    Explanations

    fishing

    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_16k_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
     აღმასრულ
    0.52
     screenplay
    0.50
    💂
    0.50
     Computing
    0.50
     ფუნქ
    0.50
    Seoul
    0.50
     newMovie
    0.49
     instytuc
    0.48
     اداروں
    0.48
    忶
    0.48
    POSITIVE LOGITS
     fishing
    1.50
     fish
    1.40
     anglers
    1.35
     Fishing
    1.30
    釣
    1.30
    fishing
    1.22
    Fishing
    1.22
     fished
    1.22
    🎣
    1.21
     angler
    1.19
    Activations Density 0.093%

    No Known Activations