© 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. 38325
    Prev
    Next
    INDEX
    Explanations

    Inter followed by angular

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

    The neuron fires on the two-space indentation tokens (i.e. the repeated “  ” whitespace marker) used to structure code blocks.

    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
     year
    -1.09
     they
    -1.07
     nalazi
    -1.04
     same
    -1.04
     summer
    -1.03
     your
    -1.03
     my
    -1.02
     Lettres
    -0.98
     month
    -0.98
     for
    -0.98
    POSITIVE LOGITS
    acakt
    1.15
     înainte
    1.14
     Lainnya
    1.08
     сейчас
    1.08
    wohnung
    1.05
    lardır
    1.05
    nél
    1.04
    🧰
    1.04
    čná
    1.04
    toFixed
    1.04
    Activations Density 0.004%

    No Known Activations