© 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. 57536
    Prev
    Next
    INDEX
    Explanations

    c# code types and syntax

    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
     esponja
    -1.20
     bandeja
    -1.19
     vegano
    -1.13
     confirme
    -1.09
     jaula
    -1.09
     “¿
    -1.07
    WHY
    -1.05
    龶
    -1.05
    頜
    -1.04
     retrofit
    -1.02
    POSITIVE LOGITS
    ?
    1.99
     Get
    1.44
     This
    1.44
     In
    1.41
     Because
    1.38
     It
    1.35
     What
    1.23
     As
    1.21
     On
    1.13
     Although
    1.13
    Activations Density 0.010%

    No Known Activations