© 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. 282
    Prev
    Next
    INDEX
    Explanations

    importance and purpose

    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
     '',
    0.16
    tı
    0.15
     triángulos
    0.15
     francés
    0.15
     \
    0.15
     三角
    0.14
     glycolysis
    0.14
     Diese
    0.14
     ထ
    0.14
     의해
    0.14
    POSITIVE LOGITS
     for
    0.27
     для
    0.25
     untuk
    0.24
     pentru
    0.24
     bagi
    0.24
     για
    0.23
    पणे
    0.22
     برای
    0.22
    для
    0.21
     enough
    0.20
    Activations Density 1.973%

    No Known Activations