© 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. 22-GEMMASCOPE-RES-131K
    4. 98302
    Prev
    Next
    INDEX
    Explanations

    investigation and zombie

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

    The neuron is keyed to “entry‐point” identifiers and initialization routines in code—e.g. includes of “main.h,” definitions of a `main()` function or a Python `__init__` method.

    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
     прилага
    -1.17
     Depois
    -1.09
     réfrig
    -1.09
     Automó
    -1.09
     Paroles
    -1.09
     hébergement
    -1.08
     Línea
    -1.06
     moteurs
    -1.04
     saham
    -1.03
    就可以了
    -1.03
    POSITIVE LOGITS
     its
    1.20
    ₤
    1.16
    imageView
    1.06
    чностью
    1.05
    interop
    1.05
    browserify
    1.03
     will
    1.02
    TypeInfo
    1.01
    EFIAPI
    1.01
    ++){
    1.00
    Activations Density 0.000%

    No Known Activations