© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 51346
    Prev
    Next
    INDEX
    Explanations

    **Weaknesses**

    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
     об
    0.51
    夋
    0.46
    кам
    0.45
     добавля
    0.45
    第三方
    0.45
    โครงการ
    0.44
    темати
    0.44
     подключа
    0.44
    盉
    0.43
     IAEA
    0.43
    POSITIVE LOGITS
    er
    0.49
     minimal
    0.44
    if
    0.44
     jef
    0.42
     indistinct
    0.42
     pouvoir
    0.41
     maximale
    0.41
     minimale
    0.41
     gris
    0.41
     Muy
    0.41
    Activations Density 0.002%

    No Known Activations