© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49593
    Prev
    Next
    INDEX
    Explanations

    programming static declarations

    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
     ワイド
    -1.09
     גם
    -1.05
    켭
    -1.03
     virtuel
    -1.01
    δό
    -1.01
    Электро
    -1.00
     células
    -1.00
     cellules
    -0.99
    轱
    -0.96
    オンライン
    -0.96
    POSITIVE LOGITS
     readonly
    1.59
     void
    1.45
     (
    1.24
     string
    1.24
     T
    1.20
     bool
    1.19
    readonly
    1.15
     in
    1.10
     CD
    1.09
     ID
    1.06
    Activations Density 0.004%

    No Known Activations