© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 46743
    Prev
    Next
    INDEX
    Explanations

    dois and academic journals

    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
    SpawnEntry
    0.41
    ოლოგი
    0.41
     ભાગ
    0.40
     sách
    0.40
     mogą
    0.39
     whitish
    0.39
     смогут
    0.39
    --");
    0.38
     निर्देशन
    0.38
    这本书
    0.38
    POSITIVE LOGITS
    /
    0.48
     Acad
    0.42
     Brookfield
    0.42
     Catch
    0.42
    laki
    0.41
    enda
    0.40
     Cours
    0.40
     History
    0.40
     Exercise
    0.40
     Jesuit
    0.40
    Activations Density 0.001%

    No Known Activations