© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53724
    Prev
    Next
    INDEX
    Explanations

    DuckDuckGo, standard deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     movieId
    0.49
    鉀
    0.46
    肆章
    0.46
    鈉
    0.45
    ভূম
    0.45
    ん
    0.45
    webtoken
    0.43
    }_\
    0.43
    CORPOR
    0.42
    fireFlower
    0.42
    POSITIVE LOGITS
    ﺒ
    0.50
     policymakers
    0.49
     and
    0.48
     inspired
    0.46
    Bald
    0.46
    .
    0.46
     ufficiale
    0.46
     longer
    0.45
    )))
    0.45
     that
    0.45
    Activations Density 0.006%

    No Known Activations