© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115657
    Prev
    Next
    INDEX
    Explanations

    multilingual content or specific non-English words

    np_acts-logits-general · gemini-2.5-flash-lite

    reporting or breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    فرم
    0.46
    FOL
    0.46
    :
    0.44
     ಅವರು
    0.42
     አይ
    0.41
    Metric
    0.41
    Cort
    0.41
    వో
    0.41
    ের
    0.40
    ))=
    0.40
    POSITIVE LOGITS
     películas
    0.52
     sağlı
    0.51
     สวัสดี
    0.50
    permal
    0.49
     소재
    0.49
     희
    0.48
    temuan
    0.46
     충
    0.46
    ضه
    0.46
     말미
    0.45
    Activations Density 0.000%

    No Known Activations