© 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. 71830
    Prev
    Next
    INDEX
    Explanations

    programming, computing, and scientific terms

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

    The neuron fires on printf‐style format specifiers (percent signs and the following specifier characters) within string literals.

    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
    ícias
    -1.30
     it
    -1.27
    oje
    -1.13
    legende
    -1.11
    bör
    -1.10
    ។
    -1.10
     ucran
    -1.09
     there
    -1.09
    )];
    -1.08
     inaprop
    -1.05
    POSITIVE LOGITS
    -
    1.17
    が
    1.12
    美味しそう
    1.07
     BACH
    1.06
    ,
    1.05
     enemmän
    1.01
    美味しく
    0.99
     herrera
    0.99
     IDEAL
    0.98
     москов
    0.97
    Activations Density 0.001%

    No Known Activations