© 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. 22-GEMMASCOPE-RES-131K
    7. 130231
    Prev
    Next
    INDEX
    Explanations

    Android UI elements

    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_22/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
     his
    -1.08
     potrivit
    -1.05
    iterranée
    -0.99
    teria
    -0.99
     These
    -0.98
     dagelijks
    -0.98
    似乎
    -0.96
    </em>
    -0.96
     where
    -0.95
     wherever
    -0.94
    POSITIVE LOGITS
     familiale
    1.20
    ⅖
    1.18
     vocale
    1.16
     enthou
    1.16
     musicales
    1.10
    เกง
    1.09
     musicale
    1.08
     natale
    1.07
     centrale
    1.06
     påvir
    1.06
    Activations Density 0.001%

    No Known Activations