© 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. 73469
    Prev
    Next
    INDEX
    Explanations

    most people know/understand/report

    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
     there
    -1.27
    section
    -1.26
     sometimes
    -1.18
    ̼
    -1.17
    ってみました
    -1.16
    ございません
    -1.16
    Weaknesses
    -1.10
    kede
    -1.09
    撓
    -1.09
     as
    -1.09
    POSITIVE LOGITS
    ↵
    1.33
     seguirá
    1.30
     biały
    1.29
    />";
    1.27
     этих
    1.23
     seguintes
    1.20
     лишь
    1.19
     starb
    1.19
    </u>
    1.18
    Color
    1.18
    Activations Density 0.118%

    No Known Activations