© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99935
    Prev
    Next
    INDEX
    Explanations

    electrical converters and regulators

    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
    {}".
    -1.51
    adomo
    -1.51
     большей
    -1.42
    '}}>
    -1.40
     *,
    -1.40
    athered
    -1.39
     irgendwo
    -1.39
    igth
    -1.38
    acheteur
    -1.38
    {}",
    -1.38
    POSITIVE LOGITS
     of
    1.63
     with
    1.55
     it
    1.50
     to
    1.34
     importante
    1.32
    都
    1.28
     vägen
    1.27
     now
    1.27
    entukan
    1.25
     bagaimana
    1.24
    Activations Density 0.030%

    No Known Activations