© 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. 245987
    Prev
    Next
    INDEX
    Explanations

    legal claims, defend or trap, cloud, your Father

    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
    N
    0.62
    ಟ
    0.55
    O
    0.54
    PKG
    0.52
    ul
    0.50
    U
    0.49
    ੂ
    0.48
    ว่าง
    0.48
    A
    0.47
    AN
    0.47
    POSITIVE LOGITS
     急
    0.50
     Sociales
    0.49
    াহিয়া
    0.49
     السي
    0.49
     Би
    0.47
     सिंघ
    0.47
     بى
    0.47
     失
    0.46
     Urgent
    0.46
     ماين
    0.44
    Activations Density 0.001%

    No Known Activations