© 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. 112584
    Prev
    Next
    INDEX
    Explanations

    Providing context or examples

    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
    ٨
    0.55
    exerc
    0.52
    вершен
    0.47
    মিক
    0.47
    abhäng
    0.47
    되면
    0.46
     чемпи
    0.46
     bénéf
    0.46
    ٣
    0.46
     കൂടുതൽ
    0.45
    POSITIVE LOGITS
     as
    0.52
     pos
    0.52
    0.49
     hali
    0.47
     pristine
    0.46
     primary
    0.43
     grub
    0.43
     saucer
    0.43
     formaldehyde
    0.43
     scrub
    0.42
    Activations Density 0.004%

    No Known Activations