© 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. 34-GEMMASCOPE-RES-131K
    4. 84714
    Prev
    Next
    INDEX
    Explanations

    "as is" BASIS

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

    The neuron fires on the “AS IS” clause (the literal “AS IS” phrase) in Apache‐style license headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    iedades
    -1.12
    zené
    -0.97
     jaya
    -0.86
    Coucou
    -0.83
    śnie
    -0.82
     اختلاف
    -0.82
     آرز
    -0.81
    uyasha
    -0.81
    ..!!
    -0.80
     鈴木
    -0.80
    POSITIVE LOGITS
     плюс
    0.84
     grupy
    0.83
    addData
    0.82
    
    0.79
     diminishing
    0.78
    Theore
    0.76
    実際
    0.74
    
    0.74
    ريقيا
    0.73
     heroic
    0.73
    Activations Density 0.003%

    No Known Activations