© 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. 48165
    Prev
    Next
    INDEX
    Explanations

    do you know the way

    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
    硞
    0.48
     texId
    0.47
    橑
    0.47
    িতেছে
    0.46
    轵
    0.46
    🧊
    0.46
    楎
    0.45
    🩺
    0.45
    𒅴
    0.45
    枌
    0.44
    POSITIVE LOGITS
    X
    0.53
     who
    0.50
    T
    0.50
    d
    0.49
    x
    0.47
     writers
    0.45
    W
    0.44
    nova
    0.44
     client
    0.43
     gran
    0.42
    Activations Density 0.013%

    No Known Activations