© 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. 34-GEMMASCOPE-RES-131K
    7. 108952
    Prev
    Next
    INDEX
    Explanations

    input type="file" accept

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

    This neuron activates on HTML `<input type="file">` form fields.

    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
     image
    -0.80
    镜像
    -0.68
    ymce
    -0.67
     nasal
    -0.66
    bmod
    -0.65
     retina
    -0.64
     cation
    -0.63
     preocupes
    -0.63
     script
    -0.63
     beard
    -0.63
    POSITIVE LOGITS
    理会
    0.65
    Protected
    0.63
     lago
    0.63
     இரு
    0.63
    ડી
    0.62
     cardinals
    0.62
    وست
    0.61
     SC
    0.61
     Referenzen
    0.61
     lounges
    0.60
    Activations Density 0.064%

    No Known Activations