© 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. 63096
    Prev
    Next
    INDEX
    Explanations

    content mode, swelling, Gate Park

    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
     Brabant
    -0.74
     excer
    -0.71
    чком
    -0.70
     restraints
    -0.69
    ruitt
    -0.66
     Valentines
    -0.66
     operativos
    -0.66
    thâu
    -0.66
     だっ
    -0.66
     याद
    -0.66
    POSITIVE LOGITS
    び
    0.70
     به
    0.70
    项目
    0.68
     Xiu
    0.66
    Fcn
    0.66
    巾
    0.66
    ளி
    0.65
    سلام
    0.65
    態
    0.65
     Fl
    0.64
    Activations Density 0.061%

    No Known Activations