© 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. 19752
    Prev
    Next
    INDEX
    Explanations

    navigational actions leading somewhere

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

    this neuron detects phrases indicating navigation or transition, such as “take(s) you to” pointing to moving to another page or location.

    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
    ↵
    -1.49
    HasForeignKey
    -1.46
    tský
    -1.34
     primeiras
    -1.27
     في
    -1.27
     necesitas
    -1.25
    の中には
    -1.23
    -1.21
    gypten
    -1.20
     estando
    -1.20
    POSITIVE LOGITS
    dámské
    1.26
    💮
    1.23
    guantes
    1.22
    㩒
    1.17
     effets
    1.16
     on
    1.15
     publicités
    1.14
    otent
    1.14
    bbbb
    1.13
     metaphorical
    1.11
    Activations Density 0.142%

    No Known Activations