© 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. 3623
    Prev
    Next
    INDEX
    Explanations

    Key improvements

    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
    ajouter
    0.43
    箴
    0.42
     ändern
    0.41
     phrasing
    0.39
     paramInt
    0.39
     його
    0.39
     Dernière
    0.39
     ajouter
    0.38
     añade
    0.38
     stimmt
    0.38
    POSITIVE LOGITS
    h
    0.42
    music
    0.39
    7
    0.39
                   
    0.38
     form
    0.38
    ch
    0.36
     trout
    0.36
    4
    0.36
    ('
    0.35
    media
    0.35
    Activations Density 0.107%

    No Known Activations