© 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. 203716
    Prev
    Next
    INDEX
    Explanations

    feature maps, system, tiles

    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
    jus
    0.52
    ilfe
    0.48
    ngth
    0.46
     तात्पर्य
    0.46
    倝
    0.45
    expenses
    0.45
     झाल
    0.45
    rás
    0.44
    ஸில்
    0.44
    Expense
    0.44
    POSITIVE LOGITS
     redact
    0.52
     river
    0.47
     transp
    0.45
     cooper
    0.44
     minister
    0.43
    ออนไลน์
    0.43
    宝
    0.43
    न्त्री
    0.42
     editor
    0.41
     verbal
    0.41
    Activations Density 0.000%

    No Known Activations