© 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. 92748
    Prev
    Next
    INDEX
    Explanations

    event or case of

    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
     великий
    -1.13
     motoru
    -1.05
     baterie
    -1.05
    hört
    -1.02
    ungguh
    -1.01
    しと
    -1.00
    corbic
    -0.99
     inteligen
    -0.98
    cím
    -0.98
     volgen
    -0.97
    POSITIVE LOGITS
     of
    5.78
     there
    1.62
     you
    1.59
     it
    1.41
    of
    1.34
     they
    1.30
     if
    1.27
    ของ
    1.22
     that
    1.18
     case
    1.16
    Activations Density 0.013%

    No Known Activations