© 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. 64279
    Prev
    Next
    INDEX
    Explanations

    I recommend

    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
    妺
    0.45
    ocarpus
    0.45
    集中
    0.44
    ครอบ
    0.42
    酲
    0.42
    บริ
    0.42
    高的
    0.41
    一层
    0.41
     pien
    0.40
    禊
    0.40
    POSITIVE LOGITS
    gages
    0.48
     మంది
    0.47
     ਟ
    0.47
     ис
    0.47
     था
    0.46
     थीं
    0.46
     formulas
    0.46
     শব্দের
    0.45
     subalgebras
    0.45
     थे
    0.44
    Activations Density 0.031%

    No Known Activations