© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83731
    Prev
    Next
    INDEX
    Explanations

    living room with features

    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
     từ
    -1.02
    UAGES
    -1.00
    των
    -0.98
     Erwartungen
    -0.96
    ობ
    -0.92
     />';
    -0.90
    كل
    -0.90
     ilyen
    -0.90
    ప్ర
    -0.89
     muualla
    -0.88
    POSITIVE LOGITS
     with
    2.66
     which
    1.41
     that
    1.37
     leading
    1.20
     flows
    1.03
    これも
    1.02
     leads
    1.02
    Orig
    0.99
     LOOKING
    0.98
     redus
    0.98
    Activations Density 0.012%

    No Known Activations