© 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. 10793
    Prev
    Next
    INDEX
    Explanations

    until I

    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
     only
    -1.41
     best
    -1.36
     never
    -1.32
     always
    -1.32
     علاوه
    -1.27
     simply
    -1.26
     sadece
    -1.24
    どういう
    -1.22
     просто
    -1.21
     twar
    -1.21
    POSITIVE LOGITS
     two
    1.70
     three
    1.57
    ستارهای
    1.51
     schuldig
    1.42
    $}}
    1.40
    обще
    1.30
    ја
    1.29
     at
    1.29
    神話
    1.28
    蛧
    1.28
    Activations Density 0.019%

    No Known Activations