© 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. 125565
    Prev
    Next
    INDEX
    Explanations

    her / she

    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
    Lunch
    0.49
    缤
    0.46
     volgens
    0.46
    ✮
    0.46
     racconto
    0.45
     théâtre
    0.44
     préparer
    0.44
     başlayalım
    0.44
     поговорим
    0.43
    တော့
    0.43
    POSITIVE LOGITS
     ini
    0.52
     laws
    0.49
     harvests
    0.49
     gacchati
    0.46
    arima
    0.46
     SMEs
    0.46
    弾
    0.44
     allowed
    0.44
     facilitates
    0.44
     caregivers
    0.44
    Activations Density 0.004%

    No Known Activations