© 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. 117894
    Prev
    Next
    INDEX
    Explanations

    matching or fitting

    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
    ینده
    -0.90
    گذاری
    -0.90
     ferry
    -0.88
     colgantes
    -0.88
     hóspedes
    -0.86
     volcán
    -0.85
    thenReturn
    -0.84
    bình
    -0.83
    ⢅
    -0.82
     răng
    -0.82
    POSITIVE LOGITS
     Conform
    1.47
     conform
    1.42
    conform
    1.38
    Conform
    1.32
     conforma
    1.23
     conforming
    1.17
     confor
    1.16
     conformity
    1.15
     conformational
    0.98
     vado
    0.93
    Activations Density 0.009%

    No Known Activations