© 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. 84064
    Prev
    Next
    INDEX
    Explanations

    protein production, aged, Director

    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
     either
    -2.16
     this
    -1.70
     its
    -1.66
     literally
    -1.65
     those
    -1.59
     entweder
    -1.59
     p
    -1.57
     these
    -1.55
     including
    -1.52
     is
    -1.48
    POSITIVE LOGITS
    Ссылка
    1.42
    诟
    1.41
     动漫
    1.38
    efter
    1.37
     rouges
    1.34
    Eks
    1.34
     白色
    1.33
     壁纸
    1.32
    orienti
    1.32
    他们的
    1.30
    Activations Density 0.202%

    No Known Activations