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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15823
    Prev
    Next
    INDEX
    Explanations

    fishing and fisheries sustainability

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

    fishing practices and sustainability

    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_31_width_262k_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
     تعلیم
    0.57
     woning
    0.56
     हाउस
    0.55
    牖
    0.54
    珽
    0.54
     വേദ
    0.53
    流畅
    0.53
    眹
    0.53
    谛
    0.52
     मकान
    0.51
    POSITIVE LOGITS
     fisheries
    1.27
     fishery
    1.24
     fishing
    1.23
     fish
    1.16
     fished
    1.16
    漁
    1.13
     fishermen
    1.09
     Fisheries
    1.09
    fishing
    1.09
     FISH
    1.05
    Activations Density 0.060%

    No Known Activations