© 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. 68646
    Prev
    Next
    INDEX
    Explanations

    reveals in, caused by, found in

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

    payments

    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
     embodied
    0.66
     bowed
    0.54
     embodies
    0.52
    F
    0.51
     Penang
    0.49
     phytochemical
    0.49
     lacquer
    0.48
     Sdn
    0.48
     Embassy
    0.47
     fabric
    0.47
    POSITIVE LOGITS
    كو
    0.51
    筁
    0.51
    م
    0.49
    也會
    0.47
    وا
    0.47
    ون
    0.47
     angepasst
    0.46
     мин
    0.46
    ቑ
    0.46
    كيل
    0.46
    Activations Density 0.000%

    No Known Activations