© 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. 12810
    Prev
    Next
    INDEX
    Explanations

    posted by [name]

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

    prepared by: name

    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
    ين
    0.56
    м
    0.51
    م
    0.51
    पौ
    0.50
     Министерство
    0.48
    پ
    0.46
    Kü
    0.46
    明确
    0.44
    রাষ্ট
    0.44
    Painter
    0.43
    POSITIVE LOGITS
    :
    0.51
     and
    0.47
     וה
    0.46
     い
    0.46
     operasi
    0.46
     hoga
    0.45
     lal
    0.44
     daly
    0.44
    ,
    0.44
     means
    0.44
    Activations Density 0.013%

    No Known Activations