© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15346
    Prev
    Next
    INDEX
    Explanations

    Stevenson wire, collect, received, damaged, NOT

    np_acts-logits-general · gemini-2.5-flash-lite

    actionable steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bane
    0.45
     definition
    0.45
     explanation
    0.45
     Our
    0.44
     dual
    0.43
    </strong>
    0.43
     precondition
    0.43
     Recap
    0.42
     froze
    0.42
     COLOR
    0.42
    POSITIVE LOGITS
    ၉
    0.51
    各国
    0.50
    lds
    0.49
    हरु
    0.48
    過了
    0.47
    صالات
    0.46
    𝒊
    0.46
    𝒈
    0.46
     スーツ
    0.46
     घटस्फोट
    0.46
    Activations Density 0.002%

    No Known Activations