© 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. 8344
    Prev
    Next
    INDEX
    Explanations

    concepts and their elaborations

    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
     using
    0.50
    )
    0.50
     reduces
    0.44
    0.44
    EN
    0.42
     to
    0.40
    0
    0.40
     used
    0.40
    或
    0.39
     would
    0.39
    POSITIVE LOGITS
     फुलकारी
    0.49
    లేదు
    0.45
     божомолдор
    0.44
     Балтбет
    0.44
     नजर
    0.41
    莜
    0.41
    遗
    0.40
    美术
    0.39
     கதாபாத்திர
    0.39
     నిర్మా
    0.39
    Activations Density 0.006%

    No Known Activations