© 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. 73420
    Prev
    Next
    INDEX
    Explanations

    major news networks

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

    the names of major TV news networks or their flagship programs (e.g. “NBC News,” “Good Morning America”).

    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
    Atlético
    -0.87
    TRIBUTES
    -0.82
    ()))
    
    -0.80
    ]})
    -0.79
    Newswire
    -0.78
    ährlich
    -0.75
     ску
    -0.75
     gossi
    -0.73
     agit
    -0.73
    "))
    
    -0.73
    POSITIVE LOGITS
     ABC
    1.28
    ABC
    1.21
     CBS
    1.11
    CBS
    1.09
     NBC
    1.04
     abc
    0.94
    abc
    0.91
     FOX
    0.89
    achio
    0.88
    าว
    0.81
    Activations Density 0.029%

    No Known Activations