© 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. 71177
    Prev
    Next
    INDEX
    Explanations

    forming structures and components

    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
    ditionally
    -1.20
    也知道
    -1.16
     it
    -1.16
     direta
    -1.16
    的情况下
    -1.13
     includes
    -1.05
     masiva
    -1.05
     inclui
    -1.05
     include
    -1.00
     alguno
    -1.00
    POSITIVE LOGITS
     which
    1.38
     kiu
    1.28
    irable
    1.22
     that
    1.20
    ⃣
    1.12
    }]
    1.11
     igra
    1.11
     bleus
    1.09
     voila
    1.09
    НЫЕ
    1.05
    Activations Density 0.120%

    No Known Activations