© 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. 10-GEMMASCOPE-RES-131K
    7. 20006
    Prev
    Next
    INDEX
    Explanations

    number prefixes

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

    The neuron is triggered by programming‐style tokens—dots, underscores, library or method names (e.g. “tf.”, “streaming_”), and numeric literals—i.e. code syntax elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    These
    -1.55
    Pengertian
    -1.48
    Ꭿ
    -1.41
     menatap
    -1.28
    Kommentare
    -1.27
     bara
    -1.25
    Additionally
    -1.24
    Inhalts
    -1.23
     rédig
    -1.23
    Unsere
    -1.22
    POSITIVE LOGITS
     this
    2.03
     three
    1.92
     how
    1.82
     it
    1.77
     what
    1.77
     each
    1.74
     five
    1.67
     six
    1.64
     four
    1.63
     every
    1.61
    Activations Density 0.004%

    No Known Activations