© 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. 3243
    Prev
    Next
    INDEX
    Explanations

    AI alter egos and names

    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
     iteratively
    0.50
    processors
    0.45
    mprj
    0.45
    analysis
    0.44
    哪些
    0.44
    包含
    0.44
    CMP
    0.44
    📑
    0.43
    overlaps
    0.42
    CONTEXT
    0.42
    POSITIVE LOGITS
     nicknamed
    0.73
     nickname
    0.64
     named
    0.59
     quien
    0.57
     fratello
    0.57
     himself
    0.56
     surname
    0.56
     Mama
    0.56
     frère
    0.56
     incarnation
    0.55
    Activations Density 0.216%

    No Known Activations