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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70517
    Prev
    Next
    INDEX
    Explanations

    html snippets and code

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

    The neuron detects appearances of the “text/html;” MIME‐type string (as in HTML meta Content-Type declarations).

    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
     include
    -1.24
    tyg
    -1.21
    gantian
    -1.19
     agricultores
    -1.12
     soltar
    -1.11
     esponja
    -1.11
     camisas
    -1.10
    نویس
    -1.09
     including
    -1.08
     camisetas
    -1.08
    POSITIVE LOGITS
    5
    1.32
    2
    1.30
    ,
    1.20
    0
    1.19
     to
    1.18
    8
    1.18
    4
    1.16
    が
    1.16
    を
    1.13
    1
    1.11
    Activations Density 0.002%

    No Known Activations