© 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. 73663
    Prev
    Next
    INDEX
    Explanations

    causal or conditional relationships

    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
    pada
    -1.03
    alties
    -1.01
     alguns
    -0.98
    ﺀ
    -0.94
     misschien
    -0.93
     eenige
    -0.93
    —¡
    -0.93
     thefe
    -0.93
    []
    
    -0.91
    Biografie
    -0.90
    POSITIVE LOGITS
     simply
    1.45
     because
    1.42
     if
    1.31
     even
    1.23
     просто
    1.20
     here
    1.19
     just
    1.18
     thanks
    1.17
     since
    1.15
     although
    1.13
    Activations Density 0.022%

    No Known Activations