© 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. 92961
    Prev
    Next
    INDEX
    Explanations

    vampire lover

    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
    ្
    0.43
     initiating
    0.43
     판단
    0.43
    bidden
    0.42
     মহাশয়ের
    0.41
     преду
    0.40
     pertaining
    0.40
     초기
    0.37
     Except
    0.37
     Sabemos
    0.36
    POSITIVE LOGITS
    ۾
    0.57
     cowork
    0.45
    NYSE
    0.44
     Millennials
    0.43
     crowns
    0.42
    accueil
    0.42
    fcast
    0.42
    ಯಲ್ಲಿ
    0.41
    ۹
    0.41
    faces
    0.41
    Activations Density 0.005%

    No Known Activations