© 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. 43058
    Prev
    Next
    INDEX
    Explanations

    burns and destruction

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

    numbers and specific details

    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
    סטי
    0.57
    蛍光
    0.51
    נו
    0.46
     نظ
    0.46
    眼神
    0.45
    最
    0.45
    ሺ
    0.43
     स्क्रीन
    0.42
    楾
    0.41
    每一个
    0.41
    POSITIVE LOGITS
     vehicles
    0.51
     inciner
    0.46
     vulcan
    0.46
     COMP
    0.45
    urno
    0.43
     vehicle
    0.43
     !,
    0.43
     generally
    0.43
    company
    0.42
     DBA
    0.42
    Activations Density 0.000%

    No Known Activations