© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 717
    Prev
    Next
    INDEX
    Explanations

    fishing and related conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     Normdatei
    0.86
    OTP
    0.84
     Allianz
    0.82
    祺
    0.77
     OTP
    0.76
    Biblioteca
    0.75
     endometrial
    0.73
    ˧
    0.72
    公演
    0.72
    ಮಾಣ
    0.71
    POSITIVE LOGITS
     fishing
    3.73
     Fishing
    3.49
    Fishing
    3.44
     fish
    3.43
     fishery
    3.42
     fishermen
    3.41
     fished
    3.37
     fisherman
    3.36
     fisheries
    3.35
    fishing
    3.32
    Activations Density 1.107%

    No Known Activations