© 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-262K
    7. 113627
    Prev
    Next
    INDEX
    Explanations

    sleep and bedtime conditions

    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_262k_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
    绕
    0.42
    体操
    0.41
     jantar
    0.38
    奂
    0.38
     smokers
    0.37
     circum
    0.36
    жда
    0.36
    ამდე
    0.36
    illac
    0.36
    척
    0.36
    POSITIVE LOGITS
    ᴵ
    0.42
    ISE
    0.41
    葺
    0.40
     Says
    0.38
    oric
    0.38
     Tid
    0.38
    篒
    0.38
     roost
    0.38
    lico
    0.37
    imported
    0.37
    Activations Density 0.030%

    No Known Activations