© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60365
    Prev
    Next
    INDEX
    Explanations

    favicon links

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

    The neuron responds to mentions of icons—especially “icon” or “favicon” references in HTML or related code.

    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
     spezielle
    -2.11
    f
    -2.00
     Then
    -1.94
     wenige
    -1.82
    ്ല
    -1.77
     comunica
    -1.73
    "};
    -1.65
    </td>
    -1.61
     rapida
    -1.58
     edili
    -1.58
    POSITIVE LOGITS
    \
    2.08
    橚
    1.87
     própri
    1.80
     comentários
    1.76
     forState
    1.73
    淠
    1.73
    ⟞
    1.70
    логу
    1.69
     cabelo
    1.67
     comentário
    1.65
    Activations Density 0.006%

    No Known Activations