© 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. 48419
    Prev
    Next
    INDEX
    Explanations

    temporal sequence after events

    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
     quella
    -1.03
     what
    -1.02
     his
    -0.91
     quello
    -0.90
     ilustracji
    -0.89
    lewood
    -0.89
    gitto
    -0.89
     Nachmittag
    -0.88
    usions
    -0.88
    nala
    -0.88
    POSITIVE LOGITS
     you
    1.91
     completion
    1.59
     it
    1.33
     they
    1.20
     the
    1.12
     completing
    1.11
     initial
    1.03
     любой
    0.96
     telah
    0.96
     đã
    0.95
    Activations Density 0.059%

    No Known Activations