© 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. 89986
    Prev
    Next
    INDEX
    Explanations

    configuration files and code

    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
     mūsų
    -0.75
    integrating
    -0.74
     daugiau
    -0.71
     wonder
    -0.70
     Hinweise
    -0.69
    avatars
    -0.69
    monedas
    -0.68
    asuring
    -0.68
    はなく
    -0.68
     Öffentlich
    -0.67
    POSITIVE LOGITS
    enabled
    1.05
    DO
    0.99
    SetActive
    0.97
    color
    0.94
    CHE
    0.87
    canvas
    0.86
    setzt
    0.83
     Castelo
    0.82
    rij
    0.80
     campeonato
    0.80
    Activations Density 0.002%

    No Known Activations