© 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. 30781
    Prev
    Next
    INDEX
    Explanations

    used to show or explain

    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
    Dine
    -0.83
    存在
    -0.82
    beschreibung
    -0.81
    eiro
    -0.81
    searched
    -0.80
    поте
    -0.79
    describing
    -0.79
     vinil
    -0.79
    ändert
    -0.78
    verfahren
    -0.78
    POSITIVE LOGITS
     evidenced
    4.63
     evident
    4.06
     reflected
    3.34
     demonstrated
    3.20
    evident
    2.97
     illustrated
    2.77
     shown
    2.67
     exemplified
    2.47
     seen
    2.39
     evidence
    2.39
    Activations Density 0.098%

    No Known Activations