© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32760
    Prev
    Next
    INDEX
    Explanations

    content type

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

    This neuron detects substrings of HTTP Content-Type (and similar) MIME declarations (e.g. “application/json”, “application/x-www-form-urlencoded,” the “/” and “x-www-form-urlencoded” pieces).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     péro
    -1.47
     suí
    -1.24
    が無い
    -1.21
     höl
    -1.21
    がなく
    -1.17
    辈子
    -1.16
    SALUD
    -1.16
     NATIONS
    -1.14
     asseg
    -1.14
    などを
    -1.14
    POSITIVE LOGITS
    Both
    1.44
     so
    1.26
     fairly
    1.23
    During
    1.23
     both
    1.21
     relatively
    1.20
     italiane
    1.20
     what
    1.16
    Quite
    1.14
    1.14
    Activations Density 0.008%
    No Known Activations