© 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-16K
    7. 2056
    Prev
    Next
    INDEX
    Explanations

    list manipulation code and punctuation

    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_16k_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
     või
    0.25
     například
    0.25
     wrongdoing
    0.24
     أو
    0.24
    烩
    0.23
     aussitôt
    0.22
    рис
    0.22
     друже
    0.22
     hãy
    0.22
    郏
    0.22
    POSITIVE LOGITS
    0.26
     terrestrial
    0.23
     hydroly
    0.22
     (~
    0.22
     κ
    0.22
     protobuf
    0.22
     retains
    0.21
     III
    0.21
     unchanged
    0.21
     obtains
    0.21
    Activations Density 1.037%

    No Known Activations