© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90547
    Prev
    Next
    INDEX
    Explanations

    Unity code and data structures

    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
     Semiconductor
    -0.71
    Collegamenti
    -0.69
    pric
    -0.68
    াঁ
    -0.67
     Convey
    -0.67
    wną
    -0.67
     Conflicts
    -0.67
     Guía
    -0.66
     scenes
    -0.66
     scene
    -0.66
    POSITIVE LOGITS
     Mathf
    0.82
    缓慢
    0.79
     beschreibt
    0.78
     Warszawie
    0.76
    aglia
    0.76
    enius
    0.71
    visuel
    0.71
    Pixels
    0.71
    DBA
    0.71
     ere
    0.70
    Activations Density 0.016%

    No Known Activations