© 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. 57354
    Prev
    Next
    INDEX
    Explanations

    potentially habitable planets

    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
     habituellement
    0.44
    ôtels
    0.43
     decrement
    0.42
    ောင်
    0.42
    asers
    0.40
    ํ
    0.40
    ﹕
    0.40
    ProductRunnable
    0.39
    谀
    0.39
    বেন
    0.39
    POSITIVE LOGITS
     उल्लंघन
    0.43
    🔥🔥
    0.42
    ,
    0.42
     uphe
    0.42
     forbidden
    0.42
    PC
    0.42
     ascended
    0.42
    iliary
    0.41
    誕生
    0.41
     доставки
    0.40
    Activations Density 0.015%

    No Known Activations