© 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. 13356
    Prev
    Next
    INDEX
    Explanations

    air, water, blood, gas flows

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

    mentions of liquids, particularly water, fluid, or gas flowing through systems.

    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
     čern
    -1.10
     guadag
    -1.07
     muertes
    -1.03
    dote
    -1.02
     التالي
    -1.02
     ngào
    -1.02
     helyez
    -1.00
    geddon
    -1.00
     ağaç
    -1.00
     demonios
    -0.98
    POSITIVE LOGITS
     from
    1.41
     contains
    1.30
     that
    1.21
    が
    1.18
    ἵ
    1.16
     viewWillAppear
    1.11
     flows
    1.09
     containing
    1.06
     flowing
    1.06
     quality
    1.04
    Activations Density 0.152%

    No Known Activations