© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65069
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and features

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

    This neuron activates on numeric tokens—especially decimal and measurement figures (e.g. “98.5,” “260,” “150,” etc.).

    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
     plaît
    -0.98
     alarg
    -0.97
    どうやら
    -0.94
     subray
    -0.93
    البته
    -0.93
    んだよ
    -0.93
     karty
    -0.91
    Strateg
    -0.90
     moviliz
    -0.89
     expresa
    -0.88
    POSITIVE LOGITS
    ここ
    1.07
    화
    1.00
    iliano
    0.96
    देश
    0.96
    𝄇
    0.95
    ಹ
    0.94
    tra
    0.94
    Function
    0.93
     fone
    0.93
    กับ
    0.91
    Activations Density 0.048%

    No Known Activations