© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    simplifying phrasing and improving flow

    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
     refiere
    0.46
     הוא
    0.38
     człowieka
    0.38
    pèce
    0.38
     hermoso
    0.38
    푦
    0.38
    явление
    0.37
    apayati
    0.37
    dimensioni
    0.37
    尧
    0.36
    POSITIVE LOGITS
     and
    0.39
    /
    0.38
     or
    0.38
     Build
    0.36
     Enable
    0.35
     Beneficial
    0.34
    ,
    0.34
     NLG
    0.33
     Resource
    0.33
     Strengthening
    0.33
    Activations Density 0.139%

    No Known Activations