© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25579
    Prev
    Next
    INDEX
    Explanations

    permitted provided

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

    The neuron detects key permission-granting terms in software license or copyright boilerplate.

    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
     forhold
    -0.71
    ̑
    -0.67
     Specialization
    -0.67
     ciri
    -0.66
    SYNOPSIS
    -0.64
    防水
    -0.63
    ędziesz
    -0.61
    理事
    -0.61
    Specialized
    -0.61
     WPF
    -0.60
    POSITIVE LOGITS
     Mega
    0.73
     Hua
    0.71
    amb
    0.71
    Gute
    0.68
     Connecticut
    0.68
    cht
    0.68
    CAC
    0.67
    øse
    0.67
    öh
    0.67
     menjalani
    0.66
    Activations Density 0.065%

    No Known Activations