© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    learning new things

    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
    anın
    0.64
     পাওয়া
    0.60
    Ги
    0.60
    abhavena
    0.59
     উপস্থিতি
    0.59
    ewną
    0.58
    t
    0.58
    at
    0.58
     봤
    0.58
     haben
    0.57
    POSITIVE LOGITS
    ;
    0.82
    د
    0.70
    い
    0.63
     to
    0.62
    ↵
    0.61
    )
    0.58
     about
    0.57
     in
    0.57
     languages
    0.55
     lessons
    0.54
    Activations Density 0.143%

    No Known Activations