© 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-262K
    7. 143066
    Prev
    Next
    INDEX
    Explanations

    blood through

    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_262k_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
     referrals
    0.45
     blossoms
    0.45
     arrests
    0.45
    dje
    0.45
    Whe
    0.44
     purchasers
    0.44
    ̣
    0.43
     collectors
    0.42
     crowns
    0.42
     invalidated
    0.42
    POSITIVE LOGITS
     mecánica
    0.52
    ס
    0.50
     μη
    0.49
     স্মার্ট
    0.48
     açı
    0.48
     навчання
    0.48
     bagno
    0.47
    禣
    0.47
    াভাব
    0.47
    س
    0.47
    Activations Density 0.002%

    No Known Activations