© 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. 83964
    Prev
    Next
    INDEX
    Explanations

    Stalker Zona anomalies

    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
     Quantitative
    -0.91
     Micro
    -0.85
     Contest
    -0.85
     Strategic
    -0.71
     Radical
    -0.71
    Contest
    -0.69
    Micro
    -0.69
    caler
    -0.69
     Betriebs
    -0.69
     Social
    -0.68
    POSITIVE LOGITS
     Stalker
    1.04
    STALK
    1.02
     stalker
    1.01
     stalk
    0.85
    Zona
    0.82
     mammo
    0.80
    alker
    0.77
    omalies
    0.77
     Zona
    0.75
     anomalies
    0.74
    Activations Density 0.013%

    No Known Activations