© 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. 37483
    Prev
    Next
    INDEX
    Explanations

    vector representations of data

    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
     distressed
    0.43
    ról
    0.41
    addSprite
    0.40
    ويل
    0.39
    僭
    0.38
     expropri
    0.38
    props
    0.37
     sewn
    0.37
     mobilized
    0.37
    <0xCF>
    0.37
    POSITIVE LOGITS
     Textbook
    0.48
     Place
    0.45
    വാദ
    0.45
     tvrd
    0.42
     Embedding
    0.42
     ह
    0.42
    斫
    0.42
     metoda
    0.42
     zaw
    0.41
     attra
    0.41
    Activations Density 0.001%

    No Known Activations