© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160404
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities

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

    data structures: list, Array, DataFrame

    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_262k_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
    icen
    0.47
     систему
    0.46
     unset
    0.46
    情况下
    0.43
    ⓒ
    0.43
    ölker
    0.42
    物流
    0.40
     instabilities
    0.40
     오래
    0.40
     चैनलों
    0.40
    POSITIVE LOGITS
    ada
    0.54
    𝐭
    0.49
     Mother
    0.49
     Rihanna
    0.48
    𝐤
    0.48
     LeBron
    0.47
     करिए
    0.47
    emer
    0.46
     mij
    0.46
    fc
    0.46
    Activations Density 0.001%

    No Known Activations