© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91751
    Prev
    Next
    INDEX
    Explanations

    pictures, facts, or sources

    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
     angefangen
    -1.45
     In
    -1.32
    例えば
    -1.26
     Namely
    -1.23
     yaitu
    -1.22
     Например
    -1.22
     Moreover
    -1.18
    例如
    -1.17
    である
    -1.16
     Within
    -1.16
    POSITIVE LOGITS
     which
    2.52
    whose
    1.77
     FBref
    1.50
     whose
    1.41
    pictured
    1.37
    another
    1.36
     tiens
    1.34
     που
    1.33
    previously
    1.33
     amarillo
    1.32
    Activations Density 0.126%

    No Known Activations