© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31975
    Prev
    Next
    INDEX
    Explanations

    collapse, collapse, fostering

    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_262k_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
     in
    0.60
    in
    0.53
     Berlin
    0.48
     giving
    0.46
     half
    0.46
     unpredictable
    0.45
    ’
    0.45
     four
    0.45
     six
    0.44
     no
    0.44
    POSITIVE LOGITS
    𝜁
    0.55
    
    0.53
    ਾਕ
    0.51
    ᇁ
    0.51
    襷
    0.50
     classement
    0.49
    
    0.49
    ێنی
    0.49
    ссо
    0.48
    ccbp
    0.48
    Activations Density 0.001%

    No Known Activations