© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58450
    Prev
    Next
    INDEX
    Explanations

    form group

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

    This neuron detects HTML markup tokens—especially tag names (like div or form) and class‐attribute fragments (such as form-group or form-control).

    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
    amat
    -0.84
    ဂ
    -0.82
    ometric
    -0.78
    mmate
    -0.78
     встречи
    -0.75
     charset
    -0.74
    ちゃん
    -0.74
     cref
    -0.73
     EMPLOYEES
    -0.72
     različ
    -0.72
    POSITIVE LOGITS
     group
    2.19
    group
    1.95
     Group
    1.76
    Group
    1.62
    GROUP
    1.60
     GROUP
    1.54
     groups
    1.35
     grupo
    1.34
     группа
    1.30
     groep
    1.25
    Activations Density 0.004%

    No Known Activations