© 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. 34-GEMMASCOPE-RES-131K
    7. 47830
    Prev
    Next
    INDEX
    Explanations

    listeners and news segments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     tulisan
    -0.90
     by
    -0.87
    ウチ
    -0.78
    README
    -0.77
    멈
    -0.73
     appears
    -0.73
    Repost
    -0.72
     tremors
    -0.71
     negotiators
    -0.70
    LPS
    -0.69
    POSITIVE LOGITS
     listener
    2.44
     Listener
    1.97
    Listener
    1.96
     listeners
    1.74
    listener
    1.65
     news
    1.59
    Listeners
    1.52
     segment
    1.48
    segment
    1.42
    Segment
    1.41
    Activations Density 0.042%

    No Known Activations