© 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. 69135
    Prev
    Next
    INDEX
    Explanations

    climbing and scaling

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

    This neuron activates on words and phrases referring to climbing or ascending—especially in the context of mountains, heights, or similar vertical movement.

    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
     =
    -1.54
    .
    -1.47
    »,
    -1.38
    ↵↵
    -1.37
    »
    -1.31
    '],$
    -1.27
    >
    -1.27
    «,
    -1.26
    BURGH
    -1.26
     «
    -1.25
    POSITIVE LOGITS
     parlato
    1.41
    rafat
    1.32
     want
    1.28
    嵛
    1.28
     sentito
    1.27
    ፳
    1.26
     on
    1.25
    UCIÓN
    1.23
     unaware
    1.22
    ditionally
    1.21
    Activations Density 0.056%

    No Known Activations