© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    sure, certainly, undeniable

    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
    :]
    0.40
    以下的
    0.40
    어진
    0.38
    '".
    0.38
    츨
    0.38
    på
    0.38
     piloted
    0.38
     comed
    0.37
     :]
    0.37
     начали
    0.37
    POSITIVE LOGITS
     sure
    0.67
     certainly
    0.64
     یقین
    0.52
    Certainly
    0.49
    Sure
    0.49
    无疑
    0.48
     நிச்சயம்
    0.47
     निश्चित
    0.47
     pewno
    0.47
     undeniable
    0.46
    Activations Density 0.005%

    No Known Activations