© 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. 1763
    Prev
    Next
    INDEX
    Explanations

    can do

    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
     ∈
    -1.20
     炖
    -1.16
    
    -1.13
     decidedly
    -1.10
    ícia
    -1.09
     crucial
    -1.08
    quite
    -1.07
     notwendi
    -1.06
    probably
    -1.05
     contratto
    -1.05
    POSITIVE LOGITS
     get
    1.87
     find
    1.70
     Somehow
    1.38
     somehow
    1.33
     make
    1.22
     or
    1.22
     afford
    1.20
     stomach
    1.19
     avoid
    1.18
     Once
    1.15
    Activations Density 0.027%

    No Known Activations