© 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. 83239
    Prev
    Next
    INDEX
    Explanations

    cue, fade, light, programming

    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
     Erick
    -0.83
    rupa
    -0.82
     migliorare
    -0.79
     Kartoffeln
    -0.79
    jetas
    -0.78
    Distances
    -0.77
    TONE
    -0.75
     پلیس
    -0.73
     Sgt
    -0.72
    нование
    -0.71
    POSITIVE LOGITS
     cues
    1.05
     fade
    0.96
    Cue
    0.95
     cue
    0.93
     programming
    0.93
    programming
    0.89
    编程
    0.88
     Fade
    0.87
     Programming
    0.86
     Fixture
    0.82
    Activations Density 0.009%

    No Known Activations