© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99706
    Prev
    Next
    INDEX
    Explanations

    river, bay, firth

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

    The neuron is detecting mentions of bodies of water (e.g. rivers, bays, reservoirs, inlets) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.36
     business
    -1.36
    atoday
    -1.29
    lloworld
    -1.26
     program
    -1.24
     context
    -1.23
     before
    -1.21
     because
    -1.19
     people
    -1.18
     programme
    -1.18
    POSITIVE LOGITS
     ничего
    1.18
    まく
    1.16
     spezi
    1.14
     справи
    1.13
    まさかの
    1.12
     précisé
    1.10
    まさか
    1.09
    ATUS
    1.09
    相変わらず
    1.08
    そも
    1.07
    Activations Density 0.056%

    No Known Activations