© 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. 34-GEMMASCOPE-RES-131K
    4. 118273
    Prev
    Next
    INDEX
    Explanations

    potential for contribution or benefit

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

    This neuron strongly detects the word “potential.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    瞩
    -1.16
    秾
    -1.12
    栳
    -1.09
    Ί
    -1.05
     Э
    -1.00
    性感
    -0.99
     poblaciones
    -0.99
     buchen
    -0.99
    kr
    -0.98
     acondicion
    -0.97
    POSITIVE LOGITS
     for
    2.00
     to
    1.59
     of
    1.56
     danger
    1.27
     tetapi
    1.16
     customers
    1.15
     exists
    1.10
     greatness
    1.10
    <em>
    1.07
    bahaya
    1.07
    Activations Density 0.028%

    No Known Activations