© 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. 63928
    Prev
    Next
    INDEX
    Explanations

    Honorable Discharge

    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
    qualification
    -0.85
    drs
    -0.81
    xls
    -0.79
     Circle
    -0.76
     qualification
    -0.76
     provavelmente
    -0.73
     hvert
    -0.73
    enheim
    -0.73
     Include
    -0.73
     стихотво
    -0.73
    POSITIVE LOGITS
     дола
    0.73
    Eph
    0.69
     strade
    0.65
    isRequired
    0.64
     Emig
    0.63
     Winslow
    0.63
    ứ
    0.62
     сверху
    0.62
     grail
    0.62
     possa
    0.61
    Activations Density 0.061%

    No Known Activations