© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106891
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and code comments

    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
     Damien
    -0.75
    ChangeEvent
    -0.74
    ंटर
    -0.72
    Damien
    -0.71
     vehículo
    -0.69
    లాలు
    -0.68
    movement
    -0.68
     Morrow
    -0.67
    Movement
    -0.67
     계
    -0.66
    POSITIVE LOGITS
    illermo
    0.68
    okola
    0.66
     asked
    0.66
    anna
    0.65
     bogs
    0.63
    فاض
    0.61
    asarray
    0.61
     Adria
    0.60
    itext
    0.60
    cionario
    0.60
    Activations Density 0.054%

    No Known Activations