© 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. 14087
    Prev
    Next
    INDEX
    Explanations

    greetings and introductions

    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
    UserProg
    0.36
    minute
    0.36
    Minute
    0.36
    ,!
    0.36
    día
    0.35
    䚰
    0.35
    elapsed
    0.35
     instrumentos
    0.34
    <unused89>
    0.34
    个月
    0.34
    POSITIVE LOGITS
    的には
    0.39
     Variability
    0.38
     Однако
    0.37
     लेकर
    0.34
     എന്നാൽ
    0.34
    蛰
    0.34
     बदलने
    0.33
    लेकिन
    0.33
     However
    0.32
     लेकिन
    0.32
    Activations Density 0.051%

    No Known Activations