© 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. 83429
    Prev
    Next
    INDEX
    Explanations

    whooping, whores, whooshing, who-knows

    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
    義務
    -0.88
     попро
    -0.82
     детям
    -0.82
    r
    -0.82
    g
    -0.79
     et
    -0.77
     年轻
    -0.76
     akzep
    -0.76
    錐
    -0.75
     sentimenti
    -0.75
    POSITIVE LOGITS
     else
    1.41
    oping
    1.30
    pper
    1.18
    pping
    1.16
    ſe
    1.14
    osh
    1.08
    lly
    1.05
    vian
    1.03
    ppers
    1.01
     knows
    0.99
    Activations Density 0.018%

    No Known Activations