© 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. 170162
    Prev
    Next
    INDEX
    Explanations

    domain-specific vocabulary

    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
    ൊന്ന
    0.49
    ية
    0.47
    curvature
    0.46
    Ridge
    0.46
    峽
    0.45
    ເລັກ
    0.44
     हड्ड
    0.43
     красивая
    0.43
    keeps
    0.43
    があります
    0.42
    POSITIVE LOGITS
     Diss
    0.55
     Narr
    0.50
    ↵
    0.46
     verdadero
    0.45
    rę
    0.43
     Dados
    0.43
    Лю
    0.43
     Beware
    0.43
    สดง
    0.42
     eind
    0.42
    Activations Density 0.000%

    No Known Activations