© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9322
    Prev
    Next
    INDEX
    Explanations

    fish tank and aquarium topics

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

    aquarium and tank

    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_40_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
    যোগ
    0.51
     सत्र
    0.44
     Hound
    0.44
    غول
    0.43
     তুরস্ক
    0.42
    呻
    0.42
    chdir
    0.41
    吠
    0.40
     विधे
    0.39
     hounds
    0.39
    POSITIVE LOGITS
     aquarium
    2.08
     Aquarium
    1.91
     aqu
    1.40
    Aqu
    1.23
     goldfish
    1.21
     Aqu
    1.20
    aqu
    1.19
     betta
    1.19
    🐠
    1.13
     tank
    1.09
    Activations Density 0.152%

    No Known Activations