© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57146
    Prev
    Next
    INDEX
    Explanations

    video editing workflows

    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
     recording
    -0.85
    αιν
    -0.79
    capture
    -0.77
    ONESIA
    -0.76
    Жан
    -0.75
     блюдо
    -0.73
    Recorded
    -0.71
     DAF
    -0.71
    RECORD
    -0.71
     capture
    -0.71
    POSITIVE LOGITS
     Ong
    0.75
    lict
    0.75
     wheel
    0.72
     Berthe
    0.70
     bie
    0.70
    ]='
    0.69
     moldura
    0.68
     Adoption
    0.68
    Wheat
    0.68
     basins
    0.67
    Activations Density 0.018%

    No Known Activations