© 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. 28553
    Prev
    Next
    INDEX
    Explanations

    Simple & descriptive options

    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
    in
    0.50
    v
    0.47
     supports
    0.46
    s
    0.45
     e
    0.43
     intimated
    0.43
     favours
    0.42
     untreated
    0.42
     Supports
    0.42
     Failed
    0.41
    POSITIVE LOGITS
     ແລະ
    0.53
     혁
    0.49
     สาว
    0.48
    conder
    0.47
    ängel
    0.47
     초기
    0.47
     ഓരോ
    0.47
     습
    0.47
     세계
    0.46
     движения
    0.46
    Activations Density 0.029%

    No Known Activations