© 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. 21148
    Prev
    Next
    INDEX
    Explanations

    firms, null, matrix, coverage

    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
     intersects
    0.37
     traceable
    0.37
    2
    0.36
     extends
    0.36
     purchasers
    0.35
     io
    0.34
     adal
    0.34
    Href
    0.34
     Docket
    0.34
     EP
    0.34
    POSITIVE LOGITS
    𝐞
    0.45
    лений
    0.41
     निरी
    0.40
     सर्वप्रथम
    0.40
    ה
    0.39
     समी
    0.39
    欵
    0.39
     Роб
    0.38
    фона
    0.38
    नाक
    0.37
    Activations Density 0.061%

    No Known Activations