© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26661
    Prev
    Next
    INDEX
    Explanations

    form action

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

    The neuron is detecting HTML form “action=” attributes (i.e. the URL assigned to a form’s action).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     comprendere
    -1.09
     alcune
    -1.09
     với
    -1.09
    孩子们
    -1.09
     seguenti
    -1.07
    但也
    -1.04
     attività
    -1.02
     behulp
    -1.02
     haup
    -1.02
     dene
    -1.02
    POSITIVE LOGITS
     but
    1.25
     here
    1.16
     сюда
    1.15
     (
    1.09
    :])
    1.08
     et
    1.05
     https
    1.05
    ktory
    1.03
     and
    1.00
    !
    1.00
    Activations Density 0.002%

    No Known Activations