© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40181
    Prev
    Next
    INDEX
    Explanations

    register addresses and assembly

    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
    ᾰ
    -1.05
     they
    -1.02
     τους
    -0.98
     Feinde
    -0.97
     durante
    -0.96
    plakat
    -0.96
    isas
    -0.96
     muñeca
    -0.95
    Provides
    -0.94
     Provides
    -0.94
    POSITIVE LOGITS
     where
    1.48
    メートル
    1.12
     there
    1.01
    pozycji
    1.01
     što
    1.00
     indicated
    0.98
    pulos
    0.97
     at
    0.97
     what
    0.95
    するか
    0.93
    Activations Density 0.009%

    No Known Activations