© 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. 108896
    Prev
    Next
    INDEX
    Explanations

    Destination, monitoring, express, transformers, reference

    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
     المستخدم
    0.43
     außer
    0.42
     trở
    0.41
    现象
    0.40
    垷
    0.40
    分别
    0.40
     eléctrico
    0.40
     đọc
    0.39
    Thời
    0.39
    推
    0.39
    POSITIVE LOGITS
     Piaget
    0.49
     moths
    0.49
    att
    0.49
     houses
    0.48
    se
    0.48
    jud
    0.47
    ing
    0.47
    oes
    0.46
     prototypes
    0.46
     yachts
    0.46
    Activations Density 0.000%

    No Known Activations