© 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. 22-GEMMASCOPE-RES-131K
    7. 65816
    Prev
    Next
    INDEX
    Explanations

    C# assembly attributes

    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
     salonu
    -1.34
    fokus
    -1.30
     réglable
    -1.27
     navideña
    -1.26
    publik
    -1.20
     réus
    -1.20
     its
    -1.20
     maleta
    -1.18
     balkon
    -1.18
    Referències
    -1.18
    POSITIVE LOGITS
     немного
    1.27
    C
    1.05
     estremamente
    1.05
    O
    1.04
     почти
    1.02
    U
    1.02
     практически
    1.01
    E
    0.99
     gespielt
    0.97
    N
    0.97
    Activations Density 0.001%

    No Known Activations