© 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. 10-GEMMASCOPE-RES-131K
    7. 8940
    Prev
    Next
    INDEX
    Explanations

    foreign words or program code

    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_10/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
    2
    -2.64
    0
    -2.64
    7
    -2.44
     ursprünglichen
    -2.31
    1
    -2.30
    5
    -2.22
    3
    -2.19
    );
    -2.13
    6
    -2.09
    尤其
    -2.05
    POSITIVE LOGITS
     auch
    2.00
     our
    2.00
     subjek
    1.98
     sapatos
    1.98
     kosme
    1.93
     konfigura
    1.91
     keram
    1.87
     akus
    1.84
     ujar
    1.84
     objek
    1.83
    Activations Density 0.000%

    No Known Activations