© 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. 104481
    Prev
    Next
    INDEX
    Explanations

    starts with Q: or E or P or N

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

    The neuron fires on long hexadecimal identifier strings (e.g. commit hashes).

    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
     mosaico
    -1.23
     poliuret
    -1.21
     pás
    -1.20
     aasta
    -1.19
     dentista
    -1.16
     emblema
    -1.14
     camisetas
    -1.14
     vela
    -1.13
    "+
    -1.13
     hablado
    -1.12
    POSITIVE LOGITS
    E
    1.22
    P
    1.19
    n
    1.19
    o
    1.16
    w
    1.15
    A
    1.15
    U
    1.14
    g
    1.13
    It
    1.12
    it
    1.09
    Activations Density 0.000%

    No Known Activations