© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80737
    Prev
    Next
    INDEX
    Explanations

    legal or valid conditions

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

    The neuron flags occurrences of “legal” or “valid” (i.e. when the text asks if something is allowed or correct by the standard).

    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
    跸
    -1.70
     destrucción
    -1.55
     (~(
    -1.47
    最为
    -1.46
     ſame
    -1.42
     ¬
    -1.39
     bloemen
    -1.38
     💪
    -1.38
    鋦
    -1.38
    LARATION
    -1.36
    POSITIVE LOGITS
     However
    1.49
     way
    1.44
     gently
    1.38
    対処
    1.38
     crafted
    1.36
     characters
    1.36
    dė
    1.36
     Additionally
    1.34
    U
    1.34
     combination
    1.31
    Activations Density 0.059%

    No Known Activations