© 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-16K
    7. 900
    Prev
    Next
    INDEX
    Explanations

    it queries the HSS

    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
     (
    0.30
    .
    0.26
    และการ
    0.25
    enhancing
    0.25
     wasteful
    0.25
     during
    0.24
     within
    0.24
    -
    0.24
    ↵↵
    0.24
    ใน
    0.24
    POSITIVE LOGITS
     really
    0.31
     opravdu
    0.29
     dość
    0.28
     tikai
    0.28
     tylko
    0.28
     mengatakan
    0.28
    本当に
    0.28
     толькі
    0.27
     tenido
    0.27
    texto
    0.27
    Activations Density 1.454%

    No Known Activations