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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34631
    Prev
    Next
    INDEX
    Explanations

    words and terms

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

    The neuron fires on the structural markers of a Q&A or quoted‐dialog format—things like “Q:”, “A:”, quotation marks, and other tokens that denote spoken or quoted segments.

    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
     Futsal
    -1.12
     nepal
    -1.06
     المسؤول
    -1.02
    rant
    -1.02
     diferite
    -1.02
    🏉
    -1.00
     vasco
    -0.98
    ְב
    -0.98
     ADVERTISING
    -0.97
    説明書
    -0.97
    POSITIVE LOGITS
    osoba
    1.41
     عندما
    1.26
     expliqué
    1.24
    衿
    1.23
     élégante
    1.23
     used
    1.19
    sigue
    1.19
    ktora
    1.18
     entregas
    1.17
    tiler
    1.16
    Activations Density 0.065%

    No Known Activations