© 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. 63544
    Prev
    Next
    INDEX
    Explanations

    questions and people's names

    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
    mayer
    -0.87
    ِ
    -0.82
    phylococcus
    -0.82
     flores
    -0.80
     until
    -0.78
    amanan
    -0.78
    ქ
    -0.76
     most
    -0.76
    נס
    -0.75
    Rohan
    -0.75
    POSITIVE LOGITS
    zaba
    0.87
     mathvariant
    0.84
    libro
    0.82
     کمتر
    0.81
    FFICIENT
    0.81
    Linking
    0.79
    Obra
    0.78
    hacer
    0.78
    daemon
    0.77
     wenig
    0.77
    Activations Density 0.000%

    No Known Activations