© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6231
    Prev
    Next
    INDEX
    Explanations

    fish, fishes, fishing

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

    fish following specific words

    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
    Algebra
    0.45
    withProperties
    0.43
    StateToProps
    0.43
     जयपुर
    0.41
    嗥
    0.40
    ieben
    0.40
    urgia
    0.39
    ClN
    0.39
     Gayatri
    0.39
     Auschwitz
    0.37
    POSITIVE LOGITS
     fish
    4.22
    魚
    3.77
    鱼
    3.72
     fishes
    3.70
     fishing
    3.69
     Fish
    3.67
     FISH
    3.67
    fish
    3.63
    Fish
    3.61
     fished
    3.59
    Activations Density 0.349%

    No Known Activations