© 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. 117752
    Prev
    Next
    INDEX
    Explanations

    contributions and findings from studies

    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
    vorschau
    -0.95
    Amazing
    -0.93
    ajaja
    -0.93
     italie
    -0.92
    entwick
    -0.91
    Brilliant
    -0.88
    konferenz
    -0.87
    denken
    -0.86
     visitantes
    -0.86
     bolsillos
    -0.85
    POSITIVE LOGITS
     contribute
    2.03
     provide
    1.84
     contributes
    1.74
     contribution
    1.71
     contributing
    1.57
     fills
    1.55
     fill
    1.53
     paving
    1.52
     valuable
    1.51
     provides
    1.46
    Activations Density 0.184%

    No Known Activations