© 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. 65297
    Prev
    Next
    INDEX
    Explanations

    Latin roots

    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
    家は
    -0.89
    もあって
    -0.88
    尽く
    -0.85
    特别是
    -0.84
    家を
    -0.81
    しかも
    -0.81
    Día
    -0.80
    つまり
    -0.80
    epresidente
    -0.80
    Ayer
    -0.80
    POSITIVE LOGITS
    Hvis
    1.12
    mă
    1.02
    Hvorfor
    1.01
     seront
    0.97
     erstmals
    0.95
    ところに
    0.93
    Når
    0.91
     zuerst
    0.90
    zł
    0.89
    際は
    0.88
    Activations Density 0.001%

    No Known Activations