© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104140
    Prev
    Next
    INDEX
    Explanations

    Nexstar, Nexenta, Lynx, Xtreme, Francesca, Thunderbird, MSM, therapeutic

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

    The neuron flags tokens containing the substring “Nex” (as in company or product names starting with “Nex”).

    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
    ↵
    -3.36
    In
    -3.22
    0
    -3.08
    <td>
    -2.89
    </strong>
    -2.89
    Also
    -2.70
    .
    -2.63
    -
    -2.50
    t
    -2.50
     tetapi
    -2.44
    POSITIVE LOGITS
    ﮦ
    3.20
    änemark
    2.97
    哢
    2.88
     are
    2.78
    ﮨ
    2.73
    
    2.70
     mauva
    2.48
     случаях
    2.45
    UTUP
    2.44
    
    2.41
    Activations Density 0.011%

    No Known Activations