© 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. 129222
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    giveness
    -1.34
     sanitaires
    -1.24
    嗐
    -1.23
    ınız
    -1.23
    gunakan
    -1.23
    ないです
    -1.23
    ございません
    -1.21
     lakukan
    -1.16
    }$)
    -1.16
     sayfas
    -1.16
    POSITIVE LOGITS
    を使い
    1.46
     I
    1.43
    <bos>
    1.41
     verur
    1.31
    showed
    1.25
    はもちろん
    1.25
     pemerintah
    1.25
    end
    1.23
     \
    1.23
    rs
    1.23
    Activations Density 0.047%

    No Known Activations