© 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. 78535
    Prev
    Next
    INDEX
    Explanations

    alumni events and publications

    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
    charCodeAt
    -0.88
     स्थ
    -0.87
    ätzliche
    -0.85
    tová
    -0.82
     Collaboration
    -0.82
    actionMode
    -0.81
    bazel
    -0.81
     круп
    -0.81
    ͌
    -0.79
    tiste
    -0.78
    POSITIVE LOGITS
     alumni
    3.56
     Alumni
    3.28
    Alumni
    3.02
     alum
    2.52
    alumni
    2.48
     reunion
    2.39
     alumnus
    2.19
    ALUM
    2.14
     ALUM
    2.13
     Alum
    2.08
    Activations Density 0.031%

    No Known Activations