© 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. 222209
    Prev
    Next
    INDEX
    Explanations

    confirmed Sloane method need

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

    browser security restrictions

    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
    ಾರು
    0.44
    সঙ্গে
    0.42
    肖
    0.42
     সঙ্গে
    0.41
    折
    0.40
    つ
    0.40
    孔
    0.39
    周
    0.39
     Geheim
    0.38
    웜
    0.38
    POSITIVE LOGITS
    oplay
    0.56
     enkele
    0.51
     necesit
    0.50
     één
    0.49
     necesitar
    0.49
     necesitas
    0.48
     exclaimed
    0.47
    oglobine
    0.47
     واحدة
    0.47
     تحتاج
    0.46
    Activations Density 0.002%

    No Known Activations