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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104703
    Prev
    Next
    INDEX
    Explanations

    aquarium and fish

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

    terms related to aquariums, fish, and aquatic environments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     السياس
    -1.52
     njia
    -1.52
    וּ
    -1.46
    🥽
    -1.34
     espirituales
    -1.34
     підприєм
    -1.32
     schutz
    -1.31
    tadiene
    -1.31
     muhimu
    -1.30
     leaft
    -1.30
    POSITIVE LOGITS
     cukru
    1.46
     botanique
    1.45
    Filmography
    1.42
     блюдо
    1.41
     сахара
    1.38
    出来ない
    1.24
    зал
    1.24
    cuatro
    1.23
     молока
    1.22
     oeste
    1.20
    Activations Density 0.023%

    No Known Activations