© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    descriptive word followed by noun/verb

    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
    內容簡介
    -1.54
    饜
    -1.54
    ungalows
    -1.41
     témoignages
    -1.38
    **(
    -1.36
     such
    -1.33
     ‘‘
    -1.32
     morgen
    -1.31
     Fg
    -1.30
     ''
    -1.28
    POSITIVE LOGITS
    set
    1.60
    ro
    1.56
    ho
    1.52
     fino
    1.52
    ve
    1.52
    </i>
    1.49
    keep
    1.49
    jusqu
    1.48
     refiere
    1.47
    鸲
    1.46
    Activations Density 0.074%

    No Known Activations