© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7666
    Prev
    Next
    INDEX
    Explanations

    registered users, topics, and posts

    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
    ↵
    -1.23
    ecznie
    -1.20
     was
    -1.16
     both
    -1.05
     like
    -1.02
    ͓
    -1.02
    かかる
    -1.01
     velours
    -1.00
     как
    -0.98
     вопросы
    -0.97
    POSITIVE LOGITS
    alties
    1.33
     that
    1.30
     alebo
    1.28
    粢
    1.25
     Depending
    1.22
     první
    1.22
    Después
    1.21
     beig
    1.21
    ※※
    1.20
    URERS
    1.18
    Activations Density 0.282%

    No Known Activations