© 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. 10-GEMMASCOPE-RES-131K
    7. 67088
    Prev
    Next
    INDEX
    Explanations

    dedicated app window

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

    The neuron fires on programming‐language constructs and keywords—e.g. class and function declarations, import/using statements, braces, and other code syntax.

    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
    וֹ
    -1.49
    💅
    -1.49
     великолеп
    -1.49
     geweldig
    -1.42
    🫶
    -1.41
    ּוֹ
    -1.41
    🤙
    -1.41
    🤟
    -1.40
     certitude
    -1.34
    ύ
    -1.33
    POSITIVE LOGITS
    ১
    1.55
     limão
    1.55
     nunca
    1.52
     trabalho
    1.41
    缺乏
    1.38
    虽然
    1.37
     плохо
    1.27
     قبل
    1.27
    没有
    1.23
     داخل
    1.23
    Activations Density 0.007%

    No Known Activations