© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15431
    Prev
    Next
    INDEX
    Explanations

    to following words

    np_acts-logits-general · gemini-2.5-flash-lite

    to more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    en
    0.49
    hlen
    0.46
    i
    0.44
    ي
    0.41
    h
    0.39
     Middleware
    0.37
     truncate
    0.36
    o
    0.36
     fmt
    0.36
     img
    0.35
    POSITIVE LOGITS
    꺅
    0.50
    शेखर
    0.48
     लेकर
    0.48
     अगदी
    0.47
    padă
    0.46
    ായക
    0.46
    ︹
    0.45
    ും
    0.45
    ἧ
    0.45
     έως
    0.45
    Activations Density 0.228%

    No Known Activations