© 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. 3269
    Prev
    Next
    INDEX
    Explanations

    data extraction, value, oceans, book, grape

    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
    לי
    0.46
    וד
    0.46
    ש
    0.44
    crast
    0.44
    ཥ
    0.43
    ני
    0.42
    רו
    0.42
    ה
    0.42
    יל
    0.42
    ма
    0.41
    POSITIVE LOGITS
     o
    0.34
     u
    0.33
     đồng
    0.31
     l
    0.31
     g
    0.31
    0.30
     c
    0.29
     So
    0.29
     ion
    0.29
     orchards
    0.29
    Activations Density 1.411%

    No Known Activations