© 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. 92027
    Prev
    Next
    INDEX
    Explanations

    typedef struct and alias

    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
    过来的
    -1.09
    对付
    -1.02
    𝐉
    -0.96
    捱
    -0.94
     finir
    -0.94
     toallas
    -0.92
    Entradas
    -0.92
     Román
    -0.91
     Ror
    -0.91
     continuación
    -0.91
    POSITIVE LOGITS
     rather
    1.40
     long
    1.31
     as
    1.00
     probably
    0.94
     has
    0.94
     a
    0.91
     plutôt
    0.90
     gesammelt
    0.89
     Rather
    0.88
     of
    0.87
    Activations Density 0.005%

    No Known Activations