© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55801
    Prev
    Next
    INDEX
    Explanations

    file, devices, PDF, movies, ssh, JPEG, format, image

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

    This neuron activates on uppercase or mixed‐case technical tokens—especially file formats, acronyms, config keys, XML/CSV/UTF labels, and other all-caps or capitalized code/config terms.

    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
    fiehlt
    -0.80
    techniques
    -0.75
    Badges
    -0.74
    kleine
    -0.70
    旬
    -0.68
     FetchType
    -0.68
    ьем
    -0.68
    弐
    -0.67
     enlace
    -0.67
     careless
    -0.67
    POSITIVE LOGITS
    (*
    1.32
     (*.
    1.09
    *.
    1.07
     *.
    1.05
    Filter
    1.02
     "*.
    1.01
     (*
    0.99
    filter
    0.98
     filter
    0.89
    OF
    0.86
    Activations Density 0.017%

    No Known Activations