© 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. 77905
    Prev
    Next
    INDEX
    Explanations

    closing a period with style

    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
     üzerinden
    -1.15
     butterknife
    -0.94
    μισ
    -0.93
    nables
    -0.93
     belangrijke
    -0.91
    erede
    -0.90
    μι
    -0.87
     Rücksicht
    -0.87
    ΤΕ
    -0.87
     betaling
    -0.87
    POSITIVE LOGITS
     with
    2.44
     by
    1.66
     on
    1.28
     style
    1.16
     stile
    1.04
     proper
    1.04
     differently
    1.03
     adequad
    1.03
     PROPER
    1.00
     appropriately
    0.98
    Activations Density 0.043%

    No Known Activations