© 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. 3646
    Prev
    Next
    INDEX
    Explanations

    state of standing behind

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

    The neuron strongly activates on words and phrases having to do with relative position or status—e.g. “standing,” “standings,” “behind,” “good standing,” “outstanding.”

    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
    -1.43
     to
    -1.33
    </h3>
    -1.25
     there
    -1.17
     '
    -1.17
     тысячи
    -1.13
     llegan
    -1.10
    t
    -1.09
     but
    -1.08
     as
    -1.06
    POSITIVE LOGITS
    鱻
    1.75
     preliminar
    1.46
    鱚
    1.44
    ഀ
    1.36
     guarn
    1.36
     adal
    1.30
    </b>
    1.29
    龗
    1.26
    塒
    1.23
     custodia
    1.23
    Activations Density 0.002%

    No Known Activations